Triple

T3210450
Position Surface form Disambiguated ID Type / Status
Subject Mike Tomlin E67264 entity
Predicate hasCoachedNotablePlayers P21067 FINISHED
Object James Harrison E144551 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: James Harrison | Statement: [Mike Tomlin, hasCoachedNotablePlayers, James Harrison]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: James Harrison
Context triple: [Mike Tomlin, hasCoachedNotablePlayers, James Harrison]
  • A. James Harrison chosen
    James Harrison is a former NFL linebacker best known for his dominant play with the Pittsburgh Steelers, including winning two Super Bowls and earning the 2008 NFL Defensive Player of the Year award.
  • B. Rodney Harrison
    Rodney Harrison is a former NFL safety best known for his hard-hitting play with the San Diego Chargers and New England Patriots and later work as a football analyst on NBC.
  • C. Andre Harris
    Andre Harris is a music producer best known for his work on Miguel's acclaimed R&B album "Kaleidoscope Dream."
  • D. Jonathan Ogden
    Jonathan Ogden is a Hall of Fame offensive tackle widely regarded as one of the greatest players in Baltimore Ravens history.
  • E. Alan Robinson
    Alan Robinson is a British computer scientist and logician best known for pioneering automated theorem proving through his development of the resolution principle and unification algorithm.
  • 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_69ad858ac36c81909962589cd277d6e2 completed March 8, 2026, 2:19 p.m.
NER Named-entity recognition batch_69adaab886c48190b72e36d0ac855ffe completed March 8, 2026, 4:58 p.m.
NED1 Entity disambiguation (via context triple) batch_69b2622d4e988190a8a98a0bc9353e3f completed March 12, 2026, 6:50 a.m.
Created at: March 8, 2026, 3:07 p.m.