Triple

T13297598
Position Surface form Disambiguated ID Type / Status
Subject Ty Law E316725 entity
Predicate name P16 FINISHED
Object Ty Law E316725 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: Ty Law | Statement: [Ty Law, name, Ty Law]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ty Law
Context triple: [Ty Law, name, Ty Law]
  • A. Ty Law chosen
    Ty Law is a former NFL cornerback best known for his Pro Bowl career with the New England Patriots and induction into the Pro Football Hall of Fame.
  • B. Andre Reed
    Andre Reed is a former NFL wide receiver best known for his prolific career and multiple Super Bowl appearances with the Buffalo Bills in the late 1980s and 1990s.
  • C. Michael Irvin
    Michael Irvin is a Hall of Fame former NFL wide receiver best known as a key offensive star of the Dallas Cowboys dynasty of the 1990s.
  • D. Darrell Green
    Darrell Green is a Hall of Fame NFL cornerback renowned for his exceptional speed and longevity during a 20-year career with Washington’s football franchise.
  • E. Keyshawn Johnson
    Keyshawn Johnson is a former NFL wide receiver and Super Bowl champion who became a prominent sports media personality and radio host.
  • 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_69d806b40ab4819094adf6c374f4811a completed April 9, 2026, 8:06 p.m.
NER Named-entity recognition batch_69d990a2f2708190a8f2aa7e7c0b92d2 completed April 11, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_69f716dd0cd88190b0ae81b402fc31cf completed May 3, 2026, 9:35 a.m.
Created at: April 9, 2026, 9:28 p.m.