Triple

T20468032
Position Surface form Disambiguated ID Type / Status
Subject The French Connection E502106 entity
Predicate author P4 FINISHED
Object Robin Moore NE NERFINISHED

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: Robin Moore | Statement: [The French Connection, author, Robin Moore]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Robin Moore
Context triple: [The French Connection, author, Robin Moore]
  • A. Robin Moore chosen
    Robin Moore was an American writer best known for his gritty, fact-based crime and military books, including the source material for the film "The French Connection."
  • B. Richard Moore
    Richard Moore was an early 17th-century English colonial administrator who became the inaugural governor of Bermuda, helping to establish the island’s first formal government.
  • C. Richard Moore
    Richard Moore was an American cinematographer known for his work on feature films in the 1960s and 1970s and as a co-founder of Panavision.
  • D. Christopher Lynn Moore
    Christopher Lynn Moore, better known by his stage name Lil Twist, is an American rapper associated with Young Money Entertainment.
  • E. Bryan Moore
    Bryan Moore is a television writer and producer best known for co-creating the Disney XD science-fiction comedy series "Lab Rats."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4ae5f1081908768b0c9a3a0bf38 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e6995e71c08190911fadbc433f0f4d completed April 20, 2026, 9:23 p.m.
Created at: April 16, 2026, 11:33 a.m.