Triple

T7465372
Position Surface form Disambiguated ID Type / Status
Subject The Horseman on the Roof E176359 entity
Predicate screenwriter P2831 FINISHED
Object Nina Companéez
Nina Companéez was a French screenwriter and film director known for her literary adaptations and character-driven dramas in French cinema and television.
E683151 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: Nina Companéez | Statement: [The Horseman on the Roof, screenwriter, Nina Companéez]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nina Companéez
Context triple: [The Horseman on the Roof, screenwriter, Nina Companéez]
  • A. Camile Velasco
    Camile Velasco is a Filipino-American singer who gained national recognition as a finalist on the third season of the television talent show American Idol.
  • B. Tess Sanchez
    Tess Sanchez is an American casting director and former head of casting at Fox, known for her work on numerous television series.
  • C. Gina Cuevas
    Gina Cuevas is a fictional character appearing in the American medical drama television series "Nurses."
  • D. Karen Peralta
    Karen Peralta is a character in the television series "Brooklyn Nine-Nine," known as the mother of main protagonist Jake Peralta.
  • E. Patricia Alvaran
    Patricia Alvaran is known as the former wife of American actor Tom Berenger.
  • 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: Nina Companéez
Triple: [The Horseman on the Roof, screenwriter, Nina Companéez]
Generated description
Nina Companéez was a French screenwriter and film director known for her literary adaptations and character-driven dramas in French cinema and television.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Nina Companéez
Target entity description: Nina Companéez was a French screenwriter and film director known for her literary adaptations and character-driven dramas in French cinema and television.
  • A. Camile Velasco
    Camile Velasco is a Filipino-American singer who gained national recognition as a finalist on the third season of the television talent show American Idol.
  • B. Tess Sanchez
    Tess Sanchez is an American casting director and former head of casting at Fox, known for her work on numerous television series.
  • C. Gina Cuevas
    Gina Cuevas is a fictional character appearing in the American medical drama television series "Nurses."
  • D. Karen Peralta
    Karen Peralta is a character in the television series "Brooklyn Nine-Nine," known as the mother of main protagonist Jake Peralta.
  • E. Patricia Alvaran
    Patricia Alvaran is known as the former wife of American actor Tom Berenger.
  • 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_69c69f21632481908bf83f6c6da897e3 completed March 27, 2026, 3:15 p.m.
NER Named-entity recognition batch_69c6f3f28f34819080713a8abcc22034 completed March 27, 2026, 9:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8ac837f948190895d136cf96951e7 completed March 29, 2026, 4:37 a.m.
NEDg Description generation batch_69c8ae3fb23881908850ac257337a131 completed March 29, 2026, 4:44 a.m.
NED2 Entity disambiguation (via description) batch_69c8aebc46e481908872d0c4c77345b5 completed March 29, 2026, 4:46 a.m.
Created at: March 27, 2026, 3:40 p.m.