6251b84d11
- Updated descriptions and comments across multiple classes to improve clarity and provide additional context. - Added alternative descriptions and structured aliases for multilingual support in classes such as Restriction, RetrievalAgent, RetrievalEvent, and others. - Improved the organization of comments and examples for better understanding of class usage and relationships. - Introduced new enum for OAI-PMH verbs and a corresponding slot to indicate supported verbs by repository endpoints. - Enhanced the RoomUnit class to clarify its purpose and usage patterns, including migration notes. - General cleanup and standardization of annotations and slot usages across various classes.
68 lines
2.5 KiB
YAML
68 lines
2.5 KiB
YAML
id: https://nde.nl/ontology/hc/class/ReasoningContent
|
|
name: reasoning_content_class
|
|
title: Reasoning Content Class
|
|
|
|
prefixes:
|
|
linkml: https://w3id.org/linkml/
|
|
hc: https://nde.nl/ontology/hc/
|
|
schema: http://schema.org/
|
|
prov: http://www.w3.org/ns/prov#
|
|
|
|
default_prefix: hc
|
|
|
|
imports:
|
|
- linkml:types
|
|
- ../slots/has_description
|
|
- ../slots/identified_by
|
|
- ../slots/has_label
|
|
|
|
classes:
|
|
ReasoningContent:
|
|
class_uri: prov:Entity
|
|
description: LLM reasoning content preserved across conversation turns.
|
|
comments:
|
|
- "Definition: represents chain-of-thought / reasoning_content produced by an LLM and retained for multi-turn context."
|
|
- "Preserved Thinking reference: https://docs.z.ai/guides/capabilities/thinking-mode"
|
|
- "Operational semantics: when preserved thinking is enabled, reasoning content from previous turns is retained in context and must be returned exactly (unmodified) to the API."
|
|
- "Migration from clear_thinking boolean: clear_thinking=false -> preserves_or_preserved: ReasoningContent with is_preserved=true; clear_thinking=true -> is_preserved=false."
|
|
- "PROV-O alignment: ReasoningContent is a prov:Entity that can be linked from an LLM response via preserves_or_preserved for provenance across turns."
|
|
- "Use cases: multi-turn agent conversations, debugging/auditing, cache-hit optimization."
|
|
- Created from slot_fixes.yaml migration (2026-01-19)
|
|
- Replaces boolean clear_thinking with structured reasoning preservation
|
|
- Enables tracking what reasoning is preserved and why
|
|
- PROV-O Entity alignment for provenance tracking
|
|
|
|
exact_mappings:
|
|
- prov:Entity
|
|
close_mappings:
|
|
- schema:Comment
|
|
- schema:Review
|
|
|
|
slots:
|
|
- has_label
|
|
- has_description
|
|
- identified_by
|
|
|
|
slot_usage:
|
|
has_label:
|
|
examples:
|
|
- value: Turn 3 Reasoning
|
|
has_description:
|
|
examples:
|
|
- value: Chain-of-thought reasoning for heritage institution extraction
|
|
identified_by:
|
|
examples:
|
|
- value: reasoning-turn-3-20260119-143000
|
|
|
|
annotations:
|
|
specificity_score: 0.8
|
|
specificity_rationale: Highly specific to LLM API reasoning preservation domain
|
|
custodian_types: '["D"]'
|
|
custodian_types_rationale: Applies to Digital Platform custodians using LLM APIs
|
|
|
|
examples:
|
|
- value:
|
|
has_label: Preserved Reasoning
|
|
- value:
|
|
has_label: Cleared Context
|
|
has_description: Fresh context for new query topic
|