Triple

T7332360
Position Surface form Disambiguated ID Type / Status
Subject Mike Keenan E169033 entity
Predicate nickname P55 FINISHED
Object Iron Mike E169033 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: Iron Mike | Statement: [Mike Keenan, nickname, Iron Mike]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Iron Mike
Context triple: [Mike Keenan, nickname, Iron Mike]
  • A. Iron Mike
    Iron Mike is the ferocious, hard-punching boxing persona of Mike Tyson, famed for his explosive power and intimidating presence in the ring.
  • B. Iron Mike chosen
    Iron Mike is the nickname of Mike Keenan, a famously intense and hard-driving former NHL head coach known for his demanding coaching style and success behind the bench.
  • C. Iron Mike
    Iron Mike is the nickname of Mike Ditka, the Hall of Fame tight end and Super Bowl–winning head coach best known for leading the Chicago Bears.
  • D. Samurai Mike
    Samurai Mike is the nickname of Mike Singletary, a Hall of Fame NFL linebacker renowned for his intense, hard-hitting play and leadership with the Chicago Bears in the 1980s.
  • E. Muscle Man
    Muscle Man is a loud, overweight, green-skinned groundskeeper known for his crude humor and "my mom" jokes in the animated series Regular Show.
  • 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_69c68a568a6481908f11e20db7bc8446 completed March 27, 2026, 1:47 p.m.
NER Named-entity recognition batch_69c6f0bf93dc8190931c13865ba827dd completed March 27, 2026, 9:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7ef1ac84c819095f03cf731f11c01 completed March 28, 2026, 3:09 p.m.
Created at: March 27, 2026, 3:03 p.m.