Triple

T12605088
Position Surface form Disambiguated ID Type / Status
Subject Running on Empty E300956 entity
Predicate producer P490 FINISHED
Object Amy Robinson E339094 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: Amy Robinson | Statement: [Running on Empty, producer, Amy Robinson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Amy Robinson
Context triple: [Running on Empty, producer, Amy Robinson]
  • A. Amy Robinson chosen
    Amy Robinson is an American actress and film producer best known for her breakout role in Martin Scorsese’s 1973 film "Mean Streets."
  • B. Susan Robinson
    Susan Robinson is best known as the wife of acclaimed British character actor Denholm Elliott.
  • C. Sarah Roberts
    Sarah Roberts is known as the spouse of Thomas Bond.
  • D. Amy Catherine Robbins
    Amy Catherine Robbins was the long-time partner and later wife of English writer H. G. Wells, known for her supportive role in his personal and professional life.
  • E. Amy Lindley
    Amy Lindley is a fictional character from the television series "Dawson's Creek," known as the daughter of Jen Lindley.
  • 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_69d7bdea2ca881908f379526c13b1145 completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d954e7f2dc8190a42cab7a0e5ea7f3 completed April 10, 2026, 7:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af45ea888190a4b2d0c1730a06ef completed May 3, 2026, 2:13 a.m.
Created at: April 9, 2026, 5:10 p.m.