Triple

T21038015
Position Surface form Disambiguated ID Type / Status
Subject Michel Litvak E518241 entity
Predicate produced P490 FINISHED
Object Legion NE NERFINISHED

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: Legion | Statement: [Michel Litvak, produced, Legion]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Legion
Context triple: [Michel Litvak, produced, Legion]
  • A. Legion
    Legion is a powerful extraterrestrial kaiju from the Gamera film series, known for its insect-like appearance and role as one of Gamera’s most formidable adversaries.
  • B. Legion
    Legion is a 1983 horror novel by William Peter Blatty that serves as a philosophical and supernatural sequel to The Exorcist, following Lieutenant Kinderman as he investigates a series of bizarre murders.
  • C. Legion
    Legion is a major Path of Exile expansion that introduced time-frozen armies from Wraeclast’s past, emphasizing large-scale combat and rewarding encounters.
  • D. Legion
    "Legion" is an acclaimed poetry collection by British poet David Harsent, noted for its dark, intricate explorations of violence, identity, and the human psyche.
  • E. Legion chosen
    "Legion" is a 2010 supernatural action-horror film in which archangel Michael defies God to protect humanity from an impending apocalypse.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b50438e08190917e2538bb8bc034 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e6fcecf2508190a7647abb3c59debb completed April 21, 2026, 4:28 a.m.
Created at: April 16, 2026, 2:05 p.m.