Triple

T6655097
Position Surface form Disambiguated ID Type / Status
Subject Tallulah Bankhead E150919 entity
Predicate spouse P13 FINISHED
Object John Emery E164721 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: John Emery | Statement: [Tallulah Bankhead, spouse, John Emery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Emery
Context triple: [Tallulah Bankhead, spouse, John Emery]
  • A. John Emery chosen
    John Emery was an American stage, film, and television actor active in the mid-20th century, often cast in sophisticated or villainous supporting roles.
  • B. Jonathan Emery
    Jonathan Emery is an actor known for his role in the film "The Iron Mistress."
  • C. Emil Foley
    Emil Foley is a tough yet principled Marine Corps drill instructor in the romantic drama film "An Officer and a Gentleman."
  • D. Richard Emery
    Richard Emery is a bishop who has served as the ecclesiastical leader of the Episcopal Diocese of North Dakota.
  • E. Anthony McHenry
    Anthony McHenry is an American professional basketball player best known for his long, successful career in Japan’s B.League, particularly as a key contributor to the Ryukyu Golden Kings.
  • 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_69c687f2c9508190a60b9aad31d3f358 completed March 27, 2026, 1:36 p.m.
NER Named-entity recognition batch_69c6b049958c8190bb3ef0d4c281825b completed March 27, 2026, 4:28 p.m.
NED1 Entity disambiguation (via context triple) batch_69c723b575a08190a3e0b1f233c36ba0 completed March 28, 2026, 12:41 a.m.
Created at: March 27, 2026, 2:01 p.m.