Triple

T22686129
Position Surface form Disambiguated ID Type / Status
Subject Wewak region E560917 entity
Predicate wasTargetedTo P69992 FINISHED
Object neutralize Japanese air power in New Guinea 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: neutralize Japanese air power in New Guinea | Statement: [Wewak region, wasTargetedTo, neutralize Japanese air power in New Guinea]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: wasTargetedTo
Context triple: [Wewak region, wasTargetedTo, neutralize Japanese air power in New Guinea]
  • A. wasTargetDuring
    Indicates that an entity served as the target of another entity or action during a specified time period or event.
  • B. targetedBecauseOf
    Indicates that one entity is made a target of an action, harm, or scrutiny specifically due to possessing a particular attribute, identity, or characteristic.
  • C. usesTarget
    Indicates that one entity employs, applies, or operates on another entity as its target or object of action.
  • D. aimedAtBy chosen
    Indicates that one entity serves as the target or goal toward which another entity directs an action, intention, or focus.
  • E. oftenTargetedBy
    Indicates that an entity is frequently chosen or subjected as the object of another entity’s actions, attention, or attacks.
  • 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_69e2454d71b48190a1f80af9f82b6fcf completed April 17, 2026, 2:35 p.m.
NER Named-entity recognition batch_69f178637bc08190a8dfb33b5f4249e5 completed April 29, 2026, 3:17 a.m.
PD Predicate disambiguation batch_69ee62b2259c819091ed1387a748b9f3 completed April 26, 2026, 7:08 p.m.
Created at: April 17, 2026, 3:12 p.m.