Triple

T36785201
Position Surface form Disambiguated ID Type / Status
Subject Homicide: The Movie E908888 entity
Predicate director P255 FINISHED
Object Jean de Segonzac
Jean de Segonzac is an American television and film director and cinematographer known for his work on gritty crime dramas and documentary-style productions.
E2209399 NE FINISHED

How this triple was built (2 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: Jean de Segonzac | Statement: [Homicide: The Movie, director, Jean de Segonzac]
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: Jean de Segonzac
Triple: [Homicide: The Movie, director, Jean de Segonzac]
Generated description
Jean de Segonzac is an American television and film director and cinematographer known for his work on gritty crime dramas and documentary-style productions.

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_69f76e7a937c81909ed7359641e670f6 completed May 3, 2026, 3:49 p.m.
NER Named-entity recognition batch_69f7c9fa78f08190add535c71143c9b5 completed May 3, 2026, 10:19 p.m.
NED1 Entity disambiguation (via context triple) batch_6a3e5746b784819097f2a4f80d6f9640 completed June 26, 2026, 10:41 a.m.
NEDg Description generation batch_6a3e58a34e688190a6e038ceea930eb8 completed June 26, 2026, 10:46 a.m.
NED2 Entity disambiguation (via description) batch_6a3e82e340948190b61755e3e1751418 completed June 26, 2026, 1:47 p.m.
Created at: May 3, 2026, 4:12 p.m.