Triple

T19627646
Position Surface form Disambiguated ID Type / Status
Subject Howie Long E471179 entity
Predicate birthName P65 FINISHED
Object Howard Matthew Moses Long NE NERFINISHED

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: Howard Matthew Moses Long | Statement: [Howie Long, birthName, Howard Matthew Moses Long]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Howard Matthew Moses Long
Context triple: [Howie Long, birthName, Howard Matthew Moses Long]
  • A. Howard Matthew Moses Long chosen
    Howard Matthew Moses Long is a former American football defensive end and Pro Football Hall of Famer who became a prominent sports analyst and actor after his NFL career.
  • B. Michael Spencer Jones
    Michael Spencer Jones is a British rock photographer best known for creating many of Oasis’s iconic album covers and promotional images during the 1990s.
  • C. Kim Moses
    Kim Moses is an American television producer best known for developing and producing the supernatural drama series "Ghost Whisperer."
  • D. Michael Carlos Jones
    Michael Carlos Jones is a songwriter best known for penning the track "No Matter What They Say."
  • E. Timothy Lewis Matthieson
    Timothy Lewis Matthieson, better known as Tim Matheson, is an American actor and director recognized for roles in films like "National Lampoon's Animal House" and the TV series "The West Wing."
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8e511f28481909f4bc3ea9191e54a completed April 10, 2026, 11:54 a.m.
NER Named-entity recognition batch_69e640eadcc48190ab5e36ddcde0c328 completed April 20, 2026, 3:06 p.m.
Created at: April 10, 2026, 1:44 p.m.