112 lines
4.5 KiB
YAML
112 lines
4.5 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: >-
|
|
Large-language-model reasoning output preserved across conversation turns for context continuity and provenance tracking.
|
|
alt_descriptions:
|
|
nl: >-
|
|
Redeneringsuitvoer van grote taalmodellen bewaard over gespreksbeurten voor contextcontinuïteit en herkomsttracking.
|
|
de: >-
|
|
Large-Language-Model-Denkausgabe, die über Gesprächsrunden hinweg für Kontextkontinuität
|
|
und Provenienzverfolgung erhalten bleibt.
|
|
fr: >-
|
|
Sortie de raisonnement de grand modèle de langage préservée entre les tours de conversation
|
|
pour la continuité contextuelle et le suivi de provenance.
|
|
es: >-
|
|
Salida de razonamiento de modelo de lenguaje grande preservada a través de turnos de conversación
|
|
para continuidad contextual y seguimiento de procedencia.
|
|
ar: >-
|
|
مخرجات استدلال نموذج اللغة الكبير المحفوظة عبر أدوار المحادثة
|
|
لاستمرارية السياق وتتبع المصدر.
|
|
id: >-
|
|
Output penalaran model bahasa besar yang dipertahankan lintas giliran percakapan
|
|
untuk kontinuitas konteks dan pelacakan provenance.
|
|
zh: >-
|
|
在对话轮次中保留的大语言模型推理输出，用于上下文连续性和来源追踪。
|
|
structured_aliases:
|
|
- literal_form: redeneerinhoud
|
|
predicate: EXACT_SYNONYM
|
|
in_language: nl
|
|
- literal_form: Denkinhalt
|
|
predicate: EXACT_SYNONYM
|
|
in_language: de
|
|
- literal_form: contenu de raisonnement
|
|
predicate: EXACT_SYNONYM
|
|
in_language: fr
|
|
- literal_form: contenido de razonamiento
|
|
predicate: EXACT_SYNONYM
|
|
in_language: es
|
|
- literal_form: محتوى الاستدلال
|
|
predicate: EXACT_SYNONYM
|
|
in_language: ar
|
|
- literal_form: konten penalaran
|
|
predicate: EXACT_SYNONYM
|
|
in_language: id
|
|
- literal_form: 推理内容
|
|
predicate: EXACT_SYNONYM
|
|
in_language: zh
|
|
broad_mappings:
|
|
- prov:Entity
|
|
close_mappings:
|
|
- schema:Comment
|
|
- schema:Review
|
|
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
|
|
- 'Preserved from prior description: LLM reasoning content preserved across conversation turns.'
|
|
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
|
|
keywords:
|
|
- LLM reasoning
|
|
- chain-of-thought
|
|
- context preservation
|
|
- multi-turn conversation
|
|
examples:
|
|
- value:
|
|
has_label: Preserved Reasoning
|
|
- value:
|
|
has_label: Cleared Context
|
|
has_description: Fresh context for new query topic
|
|
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
|