Triple

T16360163
Position Surface form Disambiguated ID Type / Status
Subject Jason Robards E397287 entity
Predicate spouse P13 FINISHED
Object Lois O’Connor E398982 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: Lois O’Connor | Statement: [Jason Robards, spouse, Lois O’Connor]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lois O’Connor
Context triple: [Jason Robards, spouse, Lois O’Connor]
  • A. Lois O’Connor chosen
    Lois O’Connor was the wife of acclaimed American stage and film actor Jason Robards.
  • B. Deirdre O'Connell
    Deirdre O'Connell is an American actress known for her extensive work in film, television, and theater, including acclaimed stage performances and character roles on screen.
  • C. Rachel O’Connor
    Rachel O’Connor is a film producer known for her work on the tennis drama movie "Challengers."
  • D. Frances O'Connor
    Frances O'Connor is an English-Australian actress known for her work in film and television, including prominent roles in dramas and period pieces.
  • E. Bridget O’Connor
    Bridget O’Connor was a British screenwriter and playwright best known for co-writing the acclaimed adaptation of John le Carré’s Tinker Tailor Soldier Spy (2011).
  • 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_69d87f2778dc8190aa95c7572db127e6 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2fad241848190a9f32c7b050f20a5 completed April 18, 2026, 3:30 a.m.
NED1 Entity disambiguation (via context triple) batch_6a006798cf488190a68cf7e57902924e completed May 10, 2026, 11:10 a.m.
Created at: April 10, 2026, 5:07 a.m.