Triple

T3197191
Position Surface form Disambiguated ID Type / Status
Subject Spellbound E66961 entity
Predicate stars P1956 FINISHED
Object Gregory Peck E8645 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: Gregory Peck | Statement: [Spellbound, stars, Gregory Peck]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gregory Peck
Context triple: [Spellbound, stars, Gregory Peck]
  • A. Gregory Peck chosen
    Gregory Peck was an acclaimed American actor renowned for his dignified, morally upright roles in classic films such as "To Kill a Mockingbird."
  • B. Montgomery Clift
    Montgomery Clift was an acclaimed American actor and early method acting pioneer, known for his intense, emotionally nuanced performances in classic films of the 1940s and 1950s.
  • C. Spencer Tracy
    Spencer Tracy was an acclaimed American film actor renowned for his naturalistic performances and two Academy Award–winning roles in a career spanning from the 1930s to the 1960s.
  • D. Gary Cooper
    Gary Cooper was an iconic American film actor renowned for his understated, stoic performances in classic Hollywood films, including major roles in Westerns and dramas.
  • E. James Stewart
    James Stewart was an iconic American film actor renowned for his everyman persona and leading roles in classic Hollywood films such as "It's a Wonderful Life," "Mr. Smith Goes to Washington," and "Vertigo."
  • 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_69ad8588ba18819086a10951c32ecb80 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69ada7192994819084817307065a25e2 completed March 8, 2026, 4:43 p.m.
NED1 Entity disambiguation (via context triple) batch_69b53fccf644819082334b566f23c20a completed March 14, 2026, 11 a.m.
Created at: March 8, 2026, 3:07 p.m.