Triple

T6263860
Position Surface form Disambiguated ID Type / Status
Subject Arnon Milchan E140363 entity
Predicate notableWork P4 FINISHED
Object Under Siege E172751 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: Under Siege | Statement: [Arnon Milchan, notableWork, Under Siege]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Under Siege
Context triple: [Arnon Milchan, notableWork, Under Siege]
  • A. Under Siege chosen
    Under Siege is a 1992 action thriller film starring Steven Seagal as a former Navy SEAL battling terrorists aboard a U.S. battleship.
  • B. Under Siege 2: Dark Territory
    Under Siege 2: Dark Territory is a 1995 action thriller film and sequel to Under Siege, featuring Steven Seagal as a former Navy SEAL battling terrorists aboard a hijacked train.
  • C. Urgent Fury
    Urgent Fury was the U.S.-led 1983 military invasion of Grenada aimed at overthrowing its Marxist government and restoring a pro-Western regime.
  • D. Cliffhanger
    Cliffhanger is a 1993 action thriller film starring Sylvester Stallone as a mountain climber caught in a high-altitude heist gone wrong.
  • E. Hudson Hawk
    Hudson Hawk is a 1991 action-comedy heist film starring Bruce Willis as a wisecracking cat burglar drawn into an absurd conspiracy involving high-tech art theft.
  • 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_69c008c95c5c819084bd3dd56133d84d completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0638c43808190a375e9f29f2b2138 completed March 22, 2026, 9:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69c2445061a481909487fdb04c50493b completed March 24, 2026, 7:59 a.m.
Created at: March 22, 2026, 4:25 p.m.