Triple

T17425722
Position Surface form Disambiguated ID Type / Status
Subject J. Lawton Collins E423731 entity
Predicate roleDuringKoreanWar P31666 FINISHED
Object Army Chief of Staff overseeing U.S. ground operations 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: Army Chief of Staff overseeing U.S. ground operations | Statement: [J. Lawton Collins, roleDuringKoreanWar, Army Chief of Staff overseeing U.S. ground operations]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: roleDuringKoreanWar
Context triple: [J. Lawton Collins, roleDuringKoreanWar, Army Chief of Staff overseeing U.S. ground operations]
  • A. roleInKoreanWar chosen
    Indicates the specific function, position, or involvement an entity had during the Korean War.
  • B. roleDuringSecondSinoJapaneseWar
    Indicates the specific role, position, or function an entity held or performed during the Second Sino-Japanese War.
  • C. roleDuringBlackHawkWar
    Indicates the specific role, position, or function an entity held during the Black Hawk War.
  • D. roleInWarOrConflict
    Indicates the specific function, position, or involvement an entity has within a particular war or conflict.
  • E. battleStarsKoreanWar
    Indicates that an entity received battle stars for its participation in the Korean War.
  • 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_69d889d88b6081908bada047f5b3ba51 completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e448fbfda88190be1c001d64289bf7 completed April 19, 2026, 3:16 a.m.
PD Predicate disambiguation batch_69e3b030eac481909b8402719cc3102e completed April 18, 2026, 4:24 p.m.
Created at: April 10, 2026, 5:46 a.m.