Triple

T4081289
Position Surface form Disambiguated ID Type / Status
Subject Tan War E87481 entity
Predicate hasCommander P1197 FINISHED
Object Michael Collins E78966 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: Michael Collins | Statement: [Tan War, hasCommander, Michael Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Michael Collins
Context triple: [Tan War, hasCommander, Michael Collins]
  • A. Michael Collins
    Michael Collins was an American astronaut and command module pilot on the historic Apollo 11 Moon landing mission.
  • B. Michael Collins chosen
    Michael Collins was a leading Irish revolutionary and statesman who played a pivotal role in the struggle for independence and the formation of the Irish Free State.
  • C. Edward D. White
    Edward D. White was the ninth Chief Justice of the United States, known for his conservative jurisprudence and influential role on the Supreme Court in the early 20th century.
  • D. Alfred M. Worden
    Alfred M. Worden was an American astronaut and test pilot best known for serving as the command module pilot on NASA's Apollo 15 lunar mission.
  • E. Edward J. White
    Edward J. White was an American film producer known for his work on mid-20th-century Westerns and genre pictures.
  • 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_69aed9435cf48190ad1da737c962d19d completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aefc5204d881909829de15015aa50d completed March 9, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69bdb8f4eab88190b123aca20feb8d63 completed March 20, 2026, 9:15 p.m.
Created at: March 9, 2026, 3:39 p.m.