Triple

T691218
Position Surface form Disambiguated ID Type / Status
Subject Battle of Pusan Perimeter E13395 entity
Predicate opponentObjective P16720 FINISHED
Object capture Pusan and destroy UN forces 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: capture Pusan and destroy UN forces | Statement: [Battle of Pusan Perimeter, opponentObjective, capture Pusan and destroy UN forces]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: opponentObjective
Context triple: [Battle of Pusan Perimeter, opponentObjective, capture Pusan and destroy UN forces]
  • A. opponentAtMidway
    Indicates that one entity is the opposing side or competitor of another in the context of the Midway event, location, or stage.
  • B. protectionObjective
    Indicates that one entity has the goal or purpose of safeguarding, defending, or preserving another entity or its interests.
  • C. opposingLocation
    Indicates that two entities are located directly opposite each other, typically across a defined reference such as a street, corridor, or boundary.
  • D. keyOpponents
    Indicates that the subject has primary or most significant opponents identified by the object.
  • E. opponentCandidate
    Indicates that one entity is a rival or competing candidate against another in the same contest or election.
  • F. None of above. chosen

Provenance (4 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_69a4933e0f98819097d22766c49b61b8 completed March 1, 2026, 7:27 p.m.
NER Named-entity recognition batch_69a4a0aebde88190a49d421477713103 completed March 1, 2026, 8:25 p.m.
PD Predicate disambiguation batch_69a49d221d38819083c0adda81f59b07 completed March 1, 2026, 8:10 p.m.
PDg Predicate description generation batch_69a49dc20880819085fa60dc1851f9dc completed March 1, 2026, 8:12 p.m.
Created at: March 1, 2026, 7:36 p.m.