980 lines
30 KiB
YAML
980 lines
30 KiB
YAML
# =============================================================================
|
|
# GLAM-NER: TEI P5 GRAPHS, NETWORKS, AND TREES MODULE
|
|
# =============================================================================
|
|
# Module: modules/advanced/tei/nets.yaml
|
|
# Parent: entity_annotation_rules_v1.7.0_unified.yaml
|
|
# Purpose: LinkML schema for TEI P5 Chapter 20 - Graphs, Networks, and Trees
|
|
# Source: TEI P5 4.10.2 (September 2025) - nets module
|
|
# =============================================================================
|
|
# This module provides LinkML class definitions for encoding graphs, networks,
|
|
# and tree structures. Essential for entity relationship modeling, knowledge
|
|
# graphs, dependency trees, and stemmatology in heritage document analysis.
|
|
# =============================================================================
|
|
|
|
id: https://w3id.org/glam/ner/tei/nets
|
|
name: glam-ner-tei-nets
|
|
title: TEI P5 Graphs, Networks, and Trees Module for GLAM-NER
|
|
version: "1.0.0"
|
|
license: https://creativecommons.org/licenses/by/4.0/
|
|
|
|
prefixes:
|
|
tei: http://www.tei-c.org/ns/1.0/
|
|
glam: https://w3id.org/glam/ner/
|
|
linkml: https://w3id.org/linkml/
|
|
crm: http://www.cidoc-crm.org/cidoc-crm/
|
|
schema: http://schema.org/
|
|
dcterms: http://purl.org/dc/terms/
|
|
skos: http://www.w3.org/2004/02/skos/core#
|
|
rdf: http://www.w3.org/1999/02/22-rdf-syntax-ns#
|
|
rdfs: http://www.w3.org/2000/01/rdf-schema#
|
|
owl: http://www.w3.org/2002/07/owl#
|
|
oa: http://www.w3.org/ns/oa#
|
|
xsd: http://www.w3.org/2001/XMLSchema#
|
|
|
|
default_prefix: glam
|
|
default_range: string
|
|
|
|
# =============================================================================
|
|
# IMPORTS
|
|
# =============================================================================
|
|
imports:
|
|
- linkml:types
|
|
|
|
# =============================================================================
|
|
# ENUMS
|
|
# =============================================================================
|
|
enums:
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Graph Types
|
|
# ---------------------------------------------------------------------------
|
|
GraphTypeEnum:
|
|
description: Types of graph structures
|
|
permissible_values:
|
|
directed:
|
|
description: Directed graph (digraph) - arcs have direction
|
|
undirected:
|
|
description: Undirected graph - edges have no direction
|
|
mixed:
|
|
description: Mixed graph with both directed and undirected connections
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Tree Types
|
|
# ---------------------------------------------------------------------------
|
|
TreeTypeEnum:
|
|
description: Types of tree structures
|
|
permissible_values:
|
|
rooted:
|
|
description: Tree with designated root node
|
|
unrooted:
|
|
description: Tree without designated root
|
|
binary:
|
|
description: Binary tree (max 2 children per node)
|
|
n-ary:
|
|
description: N-ary tree (variable children per node)
|
|
ordered:
|
|
description: Ordered tree (child order significant)
|
|
unordered:
|
|
description: Unordered tree (child order not significant)
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Node Types for NER
|
|
# ---------------------------------------------------------------------------
|
|
EntityNodeTypeEnum:
|
|
description: Types of nodes in entity relationship graphs
|
|
permissible_values:
|
|
entity:
|
|
description: Named entity node
|
|
meaning: glam:NamedEntity
|
|
mention:
|
|
description: Entity mention in text
|
|
meaning: glam:EntityMention
|
|
concept:
|
|
description: Abstract concept node
|
|
meaning: skos:Concept
|
|
event:
|
|
description: Event node
|
|
meaning: crm:E5_Event
|
|
place:
|
|
description: Place/location node
|
|
meaning: crm:E53_Place
|
|
time:
|
|
description: Temporal node
|
|
meaning: crm:E52_Time-Span
|
|
document:
|
|
description: Document node
|
|
meaning: crm:E31_Document
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Arc/Edge Types for Relations
|
|
# ---------------------------------------------------------------------------
|
|
RelationTypeEnum:
|
|
description: Types of relations/edges in entity graphs
|
|
permissible_values:
|
|
# Semantic relations
|
|
same_as:
|
|
description: Identity/coreference relation
|
|
meaning: owl:sameAs
|
|
related_to:
|
|
description: General relatedness
|
|
meaning: skos:related
|
|
broader:
|
|
description: Broader/hypernym relation
|
|
meaning: skos:broader
|
|
narrower:
|
|
description: Narrower/hyponym relation
|
|
meaning: skos:narrower
|
|
part_of:
|
|
description: Part-whole relation
|
|
meaning: dcterms:isPartOf
|
|
# Temporal relations
|
|
before:
|
|
description: Temporal precedence
|
|
after:
|
|
description: Temporal succession
|
|
during:
|
|
description: Temporal inclusion
|
|
# Spatial relations
|
|
located_in:
|
|
description: Spatial containment
|
|
meaning: crm:P89_falls_within
|
|
near:
|
|
description: Spatial proximity
|
|
# Agent relations
|
|
created_by:
|
|
description: Creator relation
|
|
meaning: dcterms:creator
|
|
participated_in:
|
|
description: Participation in event
|
|
meaning: crm:P11_had_participant
|
|
# Document relations
|
|
mentions:
|
|
description: Document mentions entity
|
|
referenced_in:
|
|
description: Entity referenced in document
|
|
# Dependency relations (for syntax trees)
|
|
nsubj:
|
|
description: Nominal subject
|
|
dobj:
|
|
description: Direct object
|
|
iobj:
|
|
description: Indirect object
|
|
nmod:
|
|
description: Nominal modifier
|
|
amod:
|
|
description: Adjectival modifier
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Stemma Types (Textual Transmission)
|
|
# ---------------------------------------------------------------------------
|
|
WitnessTypeEnum:
|
|
description: Types of textual witnesses in stemmatology
|
|
permissible_values:
|
|
archetype:
|
|
description: Hypothetical original or archetype
|
|
hyparchetype:
|
|
description: Hypothetical intermediate ancestor
|
|
extant:
|
|
description: Extant manuscript witness
|
|
lost:
|
|
description: Lost manuscript (inferred)
|
|
edition:
|
|
description: Published edition
|
|
fragment:
|
|
description: Fragmentary witness
|
|
|
|
# =============================================================================
|
|
# SLOTS
|
|
# =============================================================================
|
|
slots:
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Graph Properties
|
|
# ---------------------------------------------------------------------------
|
|
graph_type:
|
|
description: Type of graph (directed, undirected, mixed)
|
|
range: GraphTypeEnum
|
|
|
|
graph_order:
|
|
description: Number of nodes in graph
|
|
range: integer
|
|
|
|
graph_size:
|
|
description: Number of arcs/edges in graph
|
|
range: integer
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Node Properties
|
|
# ---------------------------------------------------------------------------
|
|
node_id:
|
|
description: Unique identifier for node
|
|
identifier: true
|
|
range: string
|
|
|
|
node_label:
|
|
description: Display label for node
|
|
range: string
|
|
|
|
node_type:
|
|
description: Type classification of node
|
|
range: EntityNodeTypeEnum
|
|
|
|
node_degree:
|
|
description: Number of incident arcs (undirected)
|
|
range: integer
|
|
|
|
in_degree:
|
|
description: Number of incoming arcs (directed)
|
|
range: integer
|
|
|
|
out_degree:
|
|
description: Number of outgoing arcs (directed)
|
|
range: integer
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Arc/Edge Properties
|
|
# ---------------------------------------------------------------------------
|
|
arc_from:
|
|
description: Source node of arc
|
|
range: string
|
|
|
|
arc_to:
|
|
description: Target node of arc
|
|
range: string
|
|
|
|
arc_label:
|
|
description: Label for arc/edge
|
|
range: string
|
|
|
|
relation_type:
|
|
description: Type of relation represented by arc
|
|
range: RelationTypeEnum
|
|
|
|
arc_weight:
|
|
description: Numeric weight of arc
|
|
range: float
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Tree Properties
|
|
# ---------------------------------------------------------------------------
|
|
tree_type:
|
|
description: Type of tree structure
|
|
range: TreeTypeEnum
|
|
|
|
tree_root:
|
|
description: Reference to root node
|
|
range: string
|
|
|
|
tree_depth:
|
|
description: Maximum depth of tree
|
|
range: integer
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Stemma Properties
|
|
# ---------------------------------------------------------------------------
|
|
witness_type:
|
|
description: Type of textual witness
|
|
range: WitnessTypeEnum
|
|
|
|
siglum:
|
|
description: Manuscript siglum/abbreviation
|
|
range: string
|
|
|
|
# =============================================================================
|
|
# CLASSES
|
|
# =============================================================================
|
|
classes:
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Graph (graph)
|
|
# ---------------------------------------------------------------------------
|
|
Graph:
|
|
description: >-
|
|
A graph structure consisting of nodes connected by arcs. Can be directed
|
|
or undirected. Used for representing relationships, networks, and
|
|
hierarchies.
|
|
class_uri: tei:graph
|
|
mixins:
|
|
- TEIElement
|
|
slots:
|
|
- graph_type
|
|
- graph_order
|
|
- graph_size
|
|
attributes:
|
|
label:
|
|
description: Label or title for the graph
|
|
range: string
|
|
nodes:
|
|
description: Nodes in the graph
|
|
range: Node
|
|
multivalued: true
|
|
required: true
|
|
arcs:
|
|
description: Arcs connecting nodes
|
|
range: Arc
|
|
multivalued: true
|
|
annotations:
|
|
tei_element: graph
|
|
tei_module: nets
|
|
glam_hypernym: graph_structure
|
|
ontology_mapping: rdf:Graph
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Node (node)
|
|
# ---------------------------------------------------------------------------
|
|
Node:
|
|
description: >-
|
|
A node (vertex) in a graph. May be labeled and connected to other nodes
|
|
via arcs.
|
|
class_uri: tei:node
|
|
mixins:
|
|
- TEIElement
|
|
slots:
|
|
- node_id
|
|
- node_label
|
|
- node_degree
|
|
- in_degree
|
|
- out_degree
|
|
attributes:
|
|
label:
|
|
description: Display label for node
|
|
range: Label
|
|
value:
|
|
description: Value or content of node
|
|
range: string
|
|
adj:
|
|
description: Adjacent nodes (undirected)
|
|
range: string
|
|
multivalued: true
|
|
adj_to:
|
|
description: Nodes this node points to (directed)
|
|
range: string
|
|
multivalued: true
|
|
adj_from:
|
|
description: Nodes pointing to this node (directed)
|
|
range: string
|
|
multivalued: true
|
|
children:
|
|
description: Child nodes (for trees)
|
|
range: string
|
|
multivalued: true
|
|
parent:
|
|
description: Parent node reference (for trees)
|
|
range: string
|
|
annotations:
|
|
tei_element: node
|
|
tei_module: nets
|
|
glam_hypernym: graph_node
|
|
ontology_mapping: rdfs:Resource
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Arc (arc)
|
|
# ---------------------------------------------------------------------------
|
|
Arc:
|
|
description: >-
|
|
An arc (edge) connecting two nodes in a graph. In directed graphs,
|
|
represents a connection from source to target.
|
|
class_uri: tei:arc
|
|
mixins:
|
|
- TEIElement
|
|
slots:
|
|
- arc_from
|
|
- arc_to
|
|
- arc_label
|
|
- arc_weight
|
|
attributes:
|
|
label:
|
|
description: Label for the arc
|
|
range: Label
|
|
annotations:
|
|
tei_element: arc
|
|
tei_module: nets
|
|
glam_hypernym: graph_edge
|
|
ontology_mapping: rdf:Property
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Tree (tree)
|
|
# ---------------------------------------------------------------------------
|
|
Tree:
|
|
description: >-
|
|
A tree structure - a connected acyclic graph with a designated root.
|
|
Used for hierarchies, parse trees, and organizational structures.
|
|
class_uri: tei:tree
|
|
mixins:
|
|
- TEIElement
|
|
slots:
|
|
- tree_type
|
|
- tree_root
|
|
- tree_depth
|
|
- graph_order
|
|
attributes:
|
|
label:
|
|
description: Label for the tree
|
|
range: string
|
|
root:
|
|
description: Root node of the tree
|
|
range: TreeNode
|
|
nodes:
|
|
description: All nodes in tree (alternative to root-first traversal)
|
|
range: TreeNode
|
|
multivalued: true
|
|
annotations:
|
|
tei_element: tree
|
|
tei_module: nets
|
|
glam_hypernym: tree_structure
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Tree Node (root, iNode, leaf)
|
|
# ---------------------------------------------------------------------------
|
|
TreeNode:
|
|
description: >-
|
|
A node in a tree structure. Can be root, internal node (iNode), or leaf.
|
|
class_uri: tei:eTree
|
|
mixins:
|
|
- TEIElement
|
|
slots:
|
|
- node_id
|
|
- node_label
|
|
attributes:
|
|
value:
|
|
description: Value or label at this node
|
|
range: string
|
|
children:
|
|
description: Child nodes
|
|
range: TreeNode
|
|
multivalued: true
|
|
parent_ref:
|
|
description: Reference to parent node
|
|
range: string
|
|
ord:
|
|
description: Order among siblings
|
|
range: integer
|
|
is_leaf:
|
|
description: Whether this is a leaf node
|
|
range: boolean
|
|
annotations:
|
|
tei_element: eTree
|
|
tei_module: nets
|
|
glam_hypernym: tree_node
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Root Node (root)
|
|
# ---------------------------------------------------------------------------
|
|
RootNode:
|
|
description: >-
|
|
The root node of a tree structure.
|
|
class_uri: tei:root
|
|
is_a: TreeNode
|
|
annotations:
|
|
tei_element: root
|
|
tei_module: nets
|
|
glam_hypernym: root_node
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Internal Node (iNode)
|
|
# ---------------------------------------------------------------------------
|
|
InternalNode:
|
|
description: >-
|
|
An internal (non-leaf, non-root) node in a tree.
|
|
class_uri: tei:iNode
|
|
is_a: TreeNode
|
|
annotations:
|
|
tei_element: iNode
|
|
tei_module: nets
|
|
glam_hypernym: internal_node
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Leaf Node (leaf)
|
|
# ---------------------------------------------------------------------------
|
|
LeafNode:
|
|
description: >-
|
|
A leaf (terminal) node in a tree with no children.
|
|
class_uri: tei:leaf
|
|
is_a: TreeNode
|
|
attributes:
|
|
is_leaf:
|
|
description: Always true for leaf nodes
|
|
range: boolean
|
|
ifabsent: "true"
|
|
annotations:
|
|
tei_element: leaf
|
|
tei_module: nets
|
|
glam_hypernym: leaf_node
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Label (label)
|
|
# ---------------------------------------------------------------------------
|
|
Label:
|
|
description: >-
|
|
A label or heading for a node, arc, or graph component.
|
|
class_uri: tei:label
|
|
mixins:
|
|
- TEIElement
|
|
attributes:
|
|
text:
|
|
description: Text content of label
|
|
range: string
|
|
type:
|
|
description: Type of label
|
|
range: string
|
|
annotations:
|
|
tei_element: label
|
|
tei_module: nets
|
|
glam_hypernym: label
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Forest (eForest) - Collection of Trees
|
|
# ---------------------------------------------------------------------------
|
|
Forest:
|
|
description: >-
|
|
A forest - a collection of disjoint trees.
|
|
class_uri: tei:forest
|
|
mixins:
|
|
- TEIElement
|
|
attributes:
|
|
trees:
|
|
description: Trees in the forest
|
|
range: Tree
|
|
multivalued: true
|
|
tree_count:
|
|
description: Number of trees
|
|
range: integer
|
|
annotations:
|
|
tei_element: forest
|
|
tei_module: nets
|
|
glam_hypernym: tree_forest
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# STEMMATOLOGY: Textual Transmission Trees
|
|
# ---------------------------------------------------------------------------
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Stemma (listWit + graph structure)
|
|
# ---------------------------------------------------------------------------
|
|
Stemma:
|
|
description: >-
|
|
A stemma codicum - a tree or graph representing the transmission history
|
|
of a text through manuscript witnesses.
|
|
class_uri: glam:Stemma
|
|
is_a: Graph
|
|
slots:
|
|
- tree_root
|
|
attributes:
|
|
archetype:
|
|
description: Hypothetical archetype/original
|
|
range: Witness
|
|
witnesses:
|
|
description: All witnesses in stemma
|
|
range: Witness
|
|
multivalued: true
|
|
relationships:
|
|
description: Transmission relationships
|
|
range: TransmissionRelation
|
|
multivalued: true
|
|
is_contaminated:
|
|
description: Whether stemma shows contamination
|
|
range: boolean
|
|
annotations:
|
|
tei_element: graph
|
|
tei_module: nets
|
|
glam_hypernym: stemma_codicum
|
|
ontology_mapping: crm:E33_Linguistic_Object
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Witness (witness)
|
|
# ---------------------------------------------------------------------------
|
|
Witness:
|
|
description: >-
|
|
A textual witness - a manuscript, edition, or other source in a stemma.
|
|
class_uri: tei:witness
|
|
mixins:
|
|
- TEIElement
|
|
slots:
|
|
- witness_type
|
|
- siglum
|
|
attributes:
|
|
witness_id:
|
|
description: Unique identifier
|
|
range: string
|
|
identifier: true
|
|
label:
|
|
description: Full name/description
|
|
range: string
|
|
date:
|
|
description: Date of witness
|
|
range: string
|
|
location:
|
|
description: Current location/repository
|
|
range: string
|
|
shelfmark:
|
|
description: Shelfmark or call number
|
|
range: string
|
|
is_hypothetical:
|
|
description: Whether witness is hypothetical (lost/inferred)
|
|
range: boolean
|
|
annotations:
|
|
tei_element: witness
|
|
tei_module: textcrit
|
|
glam_hypernym: textual_witness
|
|
ontology_mapping: crm:E22_Human-Made_Object
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Transmission Relation
|
|
# ---------------------------------------------------------------------------
|
|
TransmissionRelation:
|
|
description: >-
|
|
A relationship between witnesses in textual transmission (copying,
|
|
derivation, contamination).
|
|
class_uri: glam:TransmissionRelation
|
|
is_a: Arc
|
|
attributes:
|
|
ancestor:
|
|
description: Source/ancestor witness
|
|
range: string
|
|
required: true
|
|
descendant:
|
|
description: Derived/descendant witness
|
|
range: string
|
|
required: true
|
|
relation_type:
|
|
description: Type of transmission
|
|
range: TransmissionTypeEnum
|
|
is_direct:
|
|
description: Whether copying was direct
|
|
range: boolean
|
|
contamination_source:
|
|
description: Source of contamination (if applicable)
|
|
range: string
|
|
annotations:
|
|
glam_hypernym: textual_transmission
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# GLAM-NER EXTENSIONS: Entity Relationship Graphs
|
|
# ---------------------------------------------------------------------------
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Entity Relationship Graph
|
|
# ---------------------------------------------------------------------------
|
|
EntityRelationGraph:
|
|
description: >-
|
|
A knowledge graph of entities and their relationships extracted from
|
|
heritage documents. Nodes are entities, arcs are typed relations.
|
|
class_uri: glam:EntityRelationGraph
|
|
is_a: Graph
|
|
slots:
|
|
- graph_type
|
|
attributes:
|
|
source_document:
|
|
description: Source document(s) for extraction
|
|
range: string
|
|
multivalued: true
|
|
extraction_date:
|
|
description: Date of extraction
|
|
range: datetime
|
|
entity_nodes:
|
|
description: Entity nodes in graph
|
|
range: EntityNode
|
|
multivalued: true
|
|
relation_arcs:
|
|
description: Relation arcs between entities
|
|
range: RelationArc
|
|
multivalued: true
|
|
entity_count:
|
|
description: Total number of entities
|
|
range: integer
|
|
relation_count:
|
|
description: Total number of relations
|
|
range: integer
|
|
annotations:
|
|
glam_hypernym: knowledge_graph
|
|
ontology_mapping: rdf:Graph
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Entity Node
|
|
# ---------------------------------------------------------------------------
|
|
EntityNode:
|
|
description: >-
|
|
A node representing a named entity in a knowledge graph.
|
|
class_uri: glam:EntityNode
|
|
is_a: Node
|
|
slots:
|
|
- node_type
|
|
attributes:
|
|
entity_id:
|
|
description: Entity identifier
|
|
range: string
|
|
identifier: true
|
|
entity_type:
|
|
description: NER entity type (PERSON, ORG, GPE, etc.)
|
|
range: string
|
|
required: true
|
|
canonical_name:
|
|
description: Canonical/normalized name
|
|
range: string
|
|
aliases:
|
|
description: Alternative names/aliases
|
|
range: string
|
|
multivalued: true
|
|
wikidata_id:
|
|
description: Wikidata Q-number
|
|
range: string
|
|
confidence:
|
|
description: Extraction confidence score
|
|
range: float
|
|
annotations:
|
|
glam_hypernym: entity_node
|
|
ontology_mapping: crm:E1_CRM_Entity
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Relation Arc
|
|
# ---------------------------------------------------------------------------
|
|
RelationArc:
|
|
description: >-
|
|
An arc representing a relationship between two entities.
|
|
class_uri: glam:RelationArc
|
|
is_a: Arc
|
|
slots:
|
|
- relation_type
|
|
- arc_weight
|
|
attributes:
|
|
relation_id:
|
|
description: Relation identifier
|
|
range: string
|
|
source_entity:
|
|
description: Source entity ID
|
|
range: string
|
|
required: true
|
|
target_entity:
|
|
description: Target entity ID
|
|
range: string
|
|
required: true
|
|
relation_label:
|
|
description: Human-readable relation label
|
|
range: string
|
|
evidence_spans:
|
|
description: Text spans supporting this relation
|
|
range: string
|
|
multivalued: true
|
|
confidence:
|
|
description: Relation extraction confidence
|
|
range: float
|
|
is_symmetric:
|
|
description: Whether relation is symmetric
|
|
range: boolean
|
|
annotations:
|
|
glam_hypernym: relation_edge
|
|
ontology_mapping: rdf:Property
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Coreference Chain
|
|
# ---------------------------------------------------------------------------
|
|
CoreferenceChain:
|
|
description: >-
|
|
A chain of entity mentions that refer to the same entity.
|
|
class_uri: glam:CoreferenceChain
|
|
mixins:
|
|
- TEIElement
|
|
attributes:
|
|
chain_id:
|
|
description: Chain identifier
|
|
range: string
|
|
identifier: true
|
|
canonical_entity:
|
|
description: Reference to canonical entity
|
|
range: string
|
|
mentions:
|
|
description: Ordered list of coreferent mentions
|
|
range: EntityMention
|
|
multivalued: true
|
|
mention_count:
|
|
description: Number of mentions in chain
|
|
range: integer
|
|
annotations:
|
|
glam_hypernym: coreference_chain
|
|
ontology_mapping: oa:Annotation
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Entity Mention (for coreference)
|
|
# ---------------------------------------------------------------------------
|
|
EntityMention:
|
|
description: >-
|
|
A mention of an entity in text, part of a coreference chain.
|
|
class_uri: glam:EntityMention
|
|
mixins:
|
|
- TEIElement
|
|
attributes:
|
|
mention_id:
|
|
description: Mention identifier
|
|
range: string
|
|
identifier: true
|
|
surface_form:
|
|
description: Text as it appears in document
|
|
range: string
|
|
required: true
|
|
mention_type:
|
|
description: Type of mention (proper name, pronoun, nominal, etc.)
|
|
range: MentionTypeEnum
|
|
start_offset:
|
|
description: Character offset start
|
|
range: integer
|
|
end_offset:
|
|
description: Character offset end
|
|
range: integer
|
|
sentence_id:
|
|
description: Reference to containing sentence
|
|
range: string
|
|
annotations:
|
|
glam_hypernym: entity_mention
|
|
ontology_mapping: oa:TextQuoteSelector
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Dependency Parse Tree
|
|
# ---------------------------------------------------------------------------
|
|
DependencyTree:
|
|
description: >-
|
|
A dependency parse tree representing syntactic structure of a sentence.
|
|
Nodes are tokens, arcs are typed dependency relations.
|
|
class_uri: glam:DependencyTree
|
|
is_a: Tree
|
|
attributes:
|
|
sentence_id:
|
|
description: Reference to source sentence
|
|
range: string
|
|
sentence_text:
|
|
description: Original sentence text
|
|
range: string
|
|
root_token:
|
|
description: Root token of the tree
|
|
range: TokenNode
|
|
tokens:
|
|
description: All tokens as nodes
|
|
range: TokenNode
|
|
multivalued: true
|
|
dependencies:
|
|
description: Dependency relations as arcs
|
|
range: DependencyArc
|
|
multivalued: true
|
|
annotations:
|
|
glam_hypernym: dependency_tree
|
|
ontology_mapping: nif:Sentence
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Token Node (for dependency trees)
|
|
# ---------------------------------------------------------------------------
|
|
TokenNode:
|
|
description: >-
|
|
A token node in a dependency tree.
|
|
class_uri: glam:TokenNode
|
|
is_a: Node
|
|
attributes:
|
|
token_id:
|
|
description: Token position (1-indexed)
|
|
range: integer
|
|
identifier: true
|
|
form:
|
|
description: Surface form of token
|
|
range: string
|
|
required: true
|
|
lemma:
|
|
description: Lemma/base form
|
|
range: string
|
|
pos_tag:
|
|
description: Part-of-speech tag
|
|
range: string
|
|
features:
|
|
description: Morphological features
|
|
range: string
|
|
head:
|
|
description: ID of head token (0 for root)
|
|
range: integer
|
|
deprel:
|
|
description: Dependency relation to head
|
|
range: string
|
|
annotations:
|
|
glam_hypernym: token_node
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Dependency Arc
|
|
# ---------------------------------------------------------------------------
|
|
DependencyArc:
|
|
description: >-
|
|
A dependency relation arc between tokens.
|
|
class_uri: glam:DependencyArc
|
|
is_a: Arc
|
|
attributes:
|
|
head_id:
|
|
description: Head token ID
|
|
range: integer
|
|
required: true
|
|
dependent_id:
|
|
description: Dependent token ID
|
|
range: integer
|
|
required: true
|
|
deprel:
|
|
description: Dependency relation type (Universal Dependencies)
|
|
range: string
|
|
required: true
|
|
enhanced:
|
|
description: Enhanced dependency information
|
|
range: string
|
|
annotations:
|
|
glam_hypernym: dependency_arc
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Mixin: TEI Element
|
|
# ---------------------------------------------------------------------------
|
|
TEIElement:
|
|
description: Base mixin for all TEI elements
|
|
mixin: true
|
|
attributes:
|
|
xml_id:
|
|
description: XML identifier
|
|
slot_uri: dcterms:identifier
|
|
range: string
|
|
xml_lang:
|
|
description: Language code
|
|
slot_uri: dcterms:language
|
|
range: string
|
|
rend:
|
|
description: Rendition or appearance
|
|
range: string
|
|
corresp:
|
|
description: Correspondence to another element
|
|
range: string
|
|
n:
|
|
description: Number or label
|
|
range: string
|
|
|
|
# =============================================================================
|
|
# ADDITIONAL ENUMS
|
|
# =============================================================================
|
|
|
|
TransmissionTypeEnum:
|
|
description: Types of textual transmission
|
|
permissible_values:
|
|
direct_copy:
|
|
description: Direct copying from exemplar
|
|
indirect_copy:
|
|
description: Copying through lost intermediate
|
|
contamination:
|
|
description: Readings from multiple sources
|
|
correction:
|
|
description: Corrected/emended text
|
|
excerpt:
|
|
description: Excerpted/abridged text
|
|
translation:
|
|
description: Translation to another language
|
|
|
|
MentionTypeEnum:
|
|
description: Types of entity mentions
|
|
permissible_values:
|
|
proper_name:
|
|
description: Proper noun mention (John Smith)
|
|
nominal:
|
|
description: Nominal mention (the president)
|
|
pronominal:
|
|
description: Pronominal mention (he, she, it)
|
|
demonstrative:
|
|
description: Demonstrative mention (this person)
|
|
relative:
|
|
description: Relative pronoun (who, which)
|