Triple

T20069196
Position Surface form Disambiguated ID Type / Status
Subject dependency grammar E499688 entity
Predicate originatedFromWorkOf P1994 FINISHED
Object Lucien Tesnière
Lucien Tesnière was a pioneering French linguist whose work laid the foundations for modern dependency grammar and significantly influenced syntactic theory.
 E2223241 NE FINISHED

How this triple was built (3 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Lucien Tesnière | Statement: [dependency grammar, originatedFromWorkOf, Lucien Tesnière]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Lucien Tesnière
Triple: [dependency grammar, originatedFromWorkOf, Lucien Tesnière]
Generated description
Lucien Tesnière was a pioneering French linguist whose work laid the foundations for modern dependency grammar and significantly influenced syntactic theory.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: originatedFromWorkOf
Context triple: [dependency grammar, originatedFromWorkOf, Lucien Tesnière]
  • A. originalWorkFrom
    Indicates that something is derived, adapted, or based on an earlier original work created by another source.
  • B. originalWorkInstanceOf
    Indicates that an original work is a specific instance or realization of a more general work, type, or conceptual creation.
  • C. coverOfWorkBy
    Indicates that one work is a cover version or performance of another work originally created by a specified creator or artist.
  • D. influencedWork chosen
    Indicates that one work has had a significant impact on the creation, style, content, or development of another work.
  • E. networkOfOriginalWork
    Indicates that one work is part of, or derived from, the same underlying original work as another within a shared network of related creations.
  • F. None of above.

Provenance (6 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69da627770948190997f486f9a2e370f completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e664365ad0819089103b00d1cf8c9f completed April 20, 2026, 5:36 p.m.
NED1 Entity disambiguation (via context triple) batch_6a406cb47048819096c51142ec6deee5 completed June 28, 2026, 12:37 a.m.
NEDg Description generation batch_6a406db565b881909769124848e2b508 completed June 28, 2026, 12:41 a.m.
NED2 Entity disambiguation (via description) batch_6a406e2e5e00819097b90719f08951c8 completed June 28, 2026, 12:43 a.m.
PD Predicate disambiguation batch_69e54cee7a5c819084ae4ff26419833f completed April 19, 2026, 9:45 p.m.
Created at: April 11, 2026, 3:39 p.m.