Triple

T5553550
Position Surface form Disambiguated ID Type / Status
Subject Japanese destroyer Amatsukaze E145582 entity
Predicate locationTorpedoed P33335 FINISHED
Object off Makassar Strait LITERAL 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: off Makassar Strait | Statement: [Japanese destroyer Amatsukaze, locationTorpedoed, off Makassar Strait]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: locationTorpedoed
Context triple: [Japanese destroyer Amatsukaze, locationTorpedoed, off Makassar Strait]
  • A. locationOfTorpedoAttack chosen
    Indicates the place where a torpedo attack occurred or was carried out.
  • B. dateHitByTorpedo
    Indicates the specific date on which an entity was struck by a torpedo.
  • C. torpedoed
    Indicates that one entity attacked and struck another entity using a torpedo, typically causing damage or destruction.
  • D. sunkBy
    Indicates that one entity (typically a vessel or structure) was caused to sink or be destroyed in water by another entity.
  • E. fleetDestroyedBy
    Indicates that a fleet was destroyed as a direct result of actions taken by another specified entity.
  • F. None of above.

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_69c008fcaf788190bafa02a1917ee73b completed March 22, 2026, 3:21 p.m.
NER Named-entity recognition batch_69c01ff9c9c48190b5e587d58c6515d8 completed March 22, 2026, 4:59 p.m.
PD Predicate disambiguation batch_69c01b10bbf8819098655839c03b7832 completed March 22, 2026, 4:38 p.m.
Created at: March 22, 2026, 3:35 p.m.