Triple

T7572908
Position Surface form Disambiguated ID Type / Status
Subject A Single Man E179288 entity
Predicate editor P1954 FINISHED
Object Joan Sobel E179288 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: Joan Sobel | Statement: [A Single Man, editor, Joan Sobel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Joan Sobel
Context triple: [A Single Man, editor, Joan Sobel]
  • A. Joan Sobel chosen
    Joan Sobel is a film editor best known for her work on critically acclaimed films such as "A Single Man."
  • B. Sally Kornbluth
    Sally Kornbluth is an American cell biologist and academic leader who became the 18th president of the Massachusetts Institute of Technology.
  • C. Margaret Shenberg
    Margaret Shenberg was the first wife of influential Hollywood film producer and studio executive Louis B. Mayer.
  • D. Doreen Alderman
    Doreen Alderman is an American former dancer and actress best known for her past marriage to actor Kelsey Grammer.
  • E. Susan Kohner
    Susan Kohner is an American former actress best known for her Oscar-nominated role in the 1959 film "Imitation of Life."
  • 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_69c69f316e50819081a271c85c06f918 completed March 27, 2026, 3:16 p.m.
NER Named-entity recognition batch_69c6f94710a0819094508356b8d610ab completed March 27, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8be17b3ec81909fc52c5570d39fb7 completed March 29, 2026, 5:52 a.m.
Created at: March 27, 2026, 3:51 p.m.