Triple

T3797161
Position Surface form Disambiguated ID Type / Status
Subject Marc Bulger E91599 entity
Predicate name P16 FINISHED
Object Marc Bulger E91599 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: Marc Bulger | Statement: [Marc Bulger, name, Marc Bulger]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marc Bulger
Context triple: [Marc Bulger, name, Marc Bulger]
  • A. Marc Bulger chosen
    Marc Bulger is a former NFL quarterback best known for his Pro Bowl tenure with the St. Louis Rams in the 2000s.
  • B. Stephen Douglas McMichael
    Stephen Douglas "Steve" McMichael is a former American football defensive tackle, two-time Super Bowl champion with the Chicago Bears, and professional wrestler best known for his role in the legendary 1985 Bears defense and later tenure in WCW.
  • C. Kevin Hector
    Kevin Hector is a former English footballer best known as a prolific forward for Derby County during their successful era in the late 1960s and 1970s.
  • D. Robert Magaw
    Robert Magaw was a Continental Army officer during the American Revolutionary War, best known for his leadership and eventual surrender of American forces at Fort Washington in 1776.
  • E. Richard Hudnut
    Richard Hudnut was an American businessman and pioneer in the modern cosmetics and perfume industry, known for building one of the first major beauty product empires in the early 20th century.
  • 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_69aed96354f48190a768966d6bd19b04 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee7a0818481909460197929ebb8e4 completed March 9, 2026, 3:30 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4f061a9e481908d16ae0aa44e2f16 completed March 14, 2026, 5:21 a.m.
Created at: March 9, 2026, 3:15 p.m.