Triple

T6471451
Position Surface form Disambiguated ID Type / Status
Subject Edward G. Robinson E142361 entity
Predicate notableWork P4 FINISHED
Object Soylent Green E215345 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: Soylent Green | Statement: [Edward G. Robinson, notableWork, Soylent Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soylent Green
Context triple: [Edward G. Robinson, notableWork, Soylent Green]
  • A. Soylent Green chosen
    Soylent Green is a 1973 dystopian science fiction film set in an overpopulated future where a detective uncovers the horrifying secret behind a popular synthetic food product.
  • B. Slan
    Slan is a classic 1940 science fiction novel by A. E. van Vogt about a persecuted race of telepathic mutants, often cited as a landmark of the Golden Age of Science Fiction.
  • C. The Terminal Man
    The Terminal Man is a 1972 science fiction novel by Michael Crichton about a man implanted with a brain-control device that malfunctions with violent consequences.
  • D. V’Ger
    V’Ger is the immensely powerful, evolved space probe that serves as the central enigmatic antagonist in the film "Star Trek: The Motion Picture."
  • E. Zabriskie Point
    Zabriskie Point is a famous viewpoint in Death Valley National Park known for its striking eroded badlands and panoramic desert landscapes.
  • 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_69c008d3bf4c8190bcf798c5ba9d6fb3 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c06a2fd4248190a789bf0301e2860a completed March 22, 2026, 10:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c6539c93c481909bed35b68ce420d8 completed March 27, 2026, 9:53 a.m.
Created at: March 22, 2026, 4:50 p.m.