Triple

T15685622
Position Surface form Disambiguated ID Type / Status
Subject John Collins E380190 entity
Predicate name P16 FINISHED
Object John Collins E380190 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: John Collins | Statement: [John Collins, name, John Collins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: John Collins
Context triple: [John Collins, name, John Collins]
  • A. John Collins
    John Collins was a Royal Navy officer best known for his leadership in World War II naval engagements, including the Battle of Cape Spada.
  • B. John Collins chosen
    John Collins is an American professional basketball player, best known as an athletic, high-scoring forward who played alongside Trae Young on the Atlanta Hawks.
  • C. Chauncey Forward
    Chauncey Forward was a 19th-century American lawyer and Democratic politician from Pennsylvania who served in the U.S. House of Representatives.
  • D. Kelly Olynyk
    Kelly Olynyk is a Canadian professional basketball player and NBA veteran known for his versatile scoring and playmaking as a stretch big man.
  • E. Michael Carter-Williams
    Michael Carter-Williams is an American professional basketball guard best known for winning the 2013–14 NBA Rookie of the Year award with the Philadelphia 76ers.
  • 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_69d86d99e860819094b6957cde470f2c completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e04f4b73d881908ec0f21393a01969 completed April 16, 2026, 2:54 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff6ee740e08190aa048b374ea7bfa0 completed May 9, 2026, 5:29 p.m.
Created at: April 10, 2026, 4:44 a.m.