Triple

T12087536
Position Surface form Disambiguated ID Type / Status
Subject What's Eating Gilbert Grape E287845 entity
Predicate producer P490 FINISHED
Object Bertil Ohlsson E287845 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: Bertil Ohlsson | Statement: [What's Eating Gilbert Grape, producer, Bertil Ohlsson]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bertil Ohlsson
Context triple: [What's Eating Gilbert Grape, producer, Bertil Ohlsson]
  • A. Bertil Ohlsson chosen
    Bertil Ohlsson is a film producer best known for his work on the acclaimed drama "What's Eating Gilbert Grape."
  • B. Göran Andersson
    Göran Andersson is a Swedish academic and engineer known for his contributions to electric power systems and energy technology.
  • C. Bengt Jansson
    Bengt Jansson is a Swedish former speedway rider known for competing at international level during the 1960s and 1970s.
  • D. Sigvard Eklund
    Sigvard Eklund was a Swedish nuclear physicist and long-serving Director General of the International Atomic Energy Agency, recognized for his contributions to the peaceful use of nuclear energy.
  • E. Arvid Lindman
    Arvid Lindman was a Swedish conservative politician and naval officer who served twice as Prime Minister of Sweden in the early 20th century.
  • 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_69d6ab4964708190850585628b287b0c completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d91514c78c8190bc1cd569e524e8b4 completed April 10, 2026, 3:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69f61e42cd588190835b3e8160bdbba5 completed May 2, 2026, 3:54 p.m.
Created at: April 8, 2026, 9:48 p.m.