Triple

T7012229
Position Surface form Disambiguated ID Type / Status
Subject André Gide E162609 entity
Predicate notableWork P4 FINISHED
Object Corydon
Corydon is a controversial series of dialogues by André Gide that defends homosexuality by arguing for its naturalness and historical prevalence.
E635594 NE FINISHED

How this triple was built (4 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: Corydon | Statement: [André Gide, notableWork, Corydon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Corydon
Context triple: [André Gide, notableWork, Corydon]
  • A. Corydon, Indiana
    Corydon, Indiana is a historic town best known as Indiana’s first state capital and the site of the only Civil War battle fought in the state.
  • B. Kokomo
    "Kokomo" is a 1988 tropical-themed pop song by the Beach Boys that became one of their late-career hits and is widely associated with the film *Cocktail*.
  • C. Vincennes
    Vincennes is a historic commune just east of Paris, France, known for its medieval Château de Vincennes and long-standing royal connections.
  • D. Warrick
    Warrick is a surname of English origin borne by various notable individuals across fields such as music, sports, and public life.
  • E. Randolph
    Randolph is the given name of Lord Randolph Churchill, a prominent 19th-century British Conservative politician and father of Winston Churchill.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Corydon
Triple: [André Gide, notableWork, Corydon]
Generated description
Corydon is a controversial series of dialogues by André Gide that defends homosexuality by arguing for its naturalness and historical prevalence.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Corydon
Target entity description: Corydon is a controversial series of dialogues by André Gide that defends homosexuality by arguing for its naturalness and historical prevalence.
  • A. Corydon, Indiana
    Corydon, Indiana is a historic town best known as Indiana’s first state capital and the site of the only Civil War battle fought in the state.
  • B. Kokomo
    "Kokomo" is a 1988 tropical-themed pop song by the Beach Boys that became one of their late-career hits and is widely associated with the film *Cocktail*.
  • C. Vincennes
    Vincennes is a historic commune just east of Paris, France, known for its medieval Château de Vincennes and long-standing royal connections.
  • D. Warrick
    Warrick is a surname of English origin borne by various notable individuals across fields such as music, sports, and public life.
  • E. Randolph
    Randolph is the given name of Lord Randolph Churchill, a prominent 19th-century British Conservative politician and father of Winston Churchill.
  • F. None of above. chosen

Provenance (5 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_69c6885a127c8190867b059bdccf13ff completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6dc58b04c8190af4913dbaf43c3d4 completed March 27, 2026, 7:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69c76a4ff6148190a7a453328507fd6b completed March 28, 2026, 5:42 a.m.
NEDg Description generation batch_69c76c23b3f881909c4aa800690c0293 completed March 28, 2026, 5:50 a.m.
NED2 Entity disambiguation (via description) batch_69c76cb513d881909da349b4b4b88a61 completed March 28, 2026, 5:52 a.m.
Created at: March 27, 2026, 2:34 p.m.