Triple

T15602951
Position Surface form Disambiguated ID Type / Status
Subject Ingrid Harbaugh E375078 entity
Predicate name P16 FINISHED
Object Ingrid Harbaugh E375078 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: Ingrid Harbaugh | Statement: [Ingrid Harbaugh, name, Ingrid Harbaugh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ingrid Harbaugh
Context triple: [Ingrid Harbaugh, name, Ingrid Harbaugh]
  • A. Ingrid Harbaugh chosen
    Ingrid Harbaugh is the wife of longtime Baltimore Ravens head coach John Harbaugh and is known for her involvement in charitable and community activities connected to the team.
  • B. Alison Harbaugh
    Alison Harbaugh is known as the daughter of longtime Baltimore Ravens head coach John Harbaugh.
  • C. Pattie Mallette
    Pattie Mallette is a Canadian author and film producer best known as the mother of pop singer Justin Bieber.
  • D. Wendy Harris
    Wendy Harris is a character known for being the mother figure in the context of the work in which she appears.
  • E. Jeannette Belichick
    Jeannette Belichick is best known as the wife of longtime U.S. Naval Academy assistant football coach Steve Belichick and the mother of legendary NFL coach Bill Belichick.
  • 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_69d85cce25008190b13b52745fbd719b completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04e6399d88190b2c3e781667666d4 completed April 16, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff56d1607c8190a42dc664abe45b32 completed May 9, 2026, 3:46 p.m.
Created at: April 10, 2026, 4:12 a.m.