Triple

T16018072
Position Surface form Disambiguated ID Type / Status
Subject Harry Patterson E388518 entity
Predicate notableWork P4 FINISHED
Object On Dangerous Ground E388530 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: On Dangerous Ground | Statement: [Harry Patterson, notableWork, On Dangerous Ground]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: On Dangerous Ground
Context triple: [Harry Patterson, notableWork, On Dangerous Ground]
  • A. On Dangerous Ground chosen
    On Dangerous Ground is a fast-paced political thriller novel by Jack Higgins involving high-stakes espionage and international intrigue.
  • B. On Dangerous Ground
    On Dangerous Ground is a 1952 American film noir crime drama directed by Nicholas Ray, known for its dark psychological themes and stark visual style.
  • C. On Deadly Ground
    On Deadly Ground is a 1994 action film directed by and starring Steven Seagal, centered on an environmentalist oil-rig firefighter battling corporate corruption in Alaska.
  • D. Edge of Danger
    Edge of Danger is a fast-paced thriller novel by Jack Higgins that follows covert operatives entangled in international intrigue and assassination plots.
  • E. Green for Danger
    Green for Danger is a 1946 British mystery film set in a wartime hospital, renowned for its blend of whodunit suspense and dark humor.
  • 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_69d86dabcb7c8190b6a39d6831d2fa1b completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e18296a7008190b72ab2ab02d0fbc9 completed April 17, 2026, 12:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69ffdbcdf2548190999a6d093c7fb64a completed May 10, 2026, 1:13 a.m.
Created at: April 10, 2026, 4:55 a.m.