Triple

T9539744
Position Surface form Disambiguated ID Type / Status
Subject The Lady Eve E230118 entity
Predicate producer P490 FINISHED
Object Paul Jones E456159 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: Paul Jones | Statement: [The Lady Eve, producer, Paul Jones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Jones
Context triple: [The Lady Eve, producer, Paul Jones]
  • A. Paul Jones chosen
    Paul Jones was a film producer best known for his work on classic Hollywood comedies, including several Bing Crosby and Bob Hope "Road to..." films.
  • B. Eric Jones
    Eric Jones is a fictional character from the novel "Another Country" by James Baldwin.
  • C. Pat Jones
    Pat Jones is an American football coach best known for his long tenure as head coach at Oklahoma State University during the 1980s and early 1990s.
  • D. Ian Jones
    Ian Jones is an Australian screenwriter best known for co-writing the acclaimed Indigenous-themed film "Ten Canoes."
  • E. Mark Jones
    Mark Jones was an English footballer for Manchester United and England who died in the 1958 Munich air disaster.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca847b1b3081908f72bc932c17cc41 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd98e4df6c8190a4d1160c42daa45f completed April 1, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69d14c5da5a081909d646c69d5de8e18 completed April 4, 2026, 5:37 p.m.
Created at: March 30, 2026, 8:01 p.m.