Triple

T12855834
Position Surface form Disambiguated ID Type / Status
Subject 1989 Patrick Division Finals E307451 entity
Predicate locationTeam2City P16075 FINISHED
Object Pittsburgh E19280 NE FINISHED

How this triple was built (3 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: Pittsburgh | Statement: [1989 Patrick Division Finals, locationTeam2City, Pittsburgh]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pittsburgh
Context triple: [1989 Patrick Division Finals, locationTeam2City, Pittsburgh]
  • A. Pittsburg
    Pittsburg is an industrial and residential city in Contra Costa County in the San Francisco Bay Area of California.
  • B. Pittsburgh, Pennsylvania chosen
    Pittsburgh, Pennsylvania is a major U.S. city in western Pennsylvania known for its historic steel industry, numerous bridges, and strong educational and technology sectors.
  • C. PGH
    PGH is the Philippine General Hospital, a major government-owned tertiary referral and teaching hospital in Manila affiliated with the University of the Philippines.
  • D. Duquesne, Pennsylvania
    Duquesne, Pennsylvania is a small industrial city along the Monongahela River near Pittsburgh, historically known as a major steel-producing community in the American Rust Belt.
  • E. Oakland, Pittsburgh
    Oakland is a major Pittsburgh neighborhood known as the city’s academic and medical hub, home to institutions like the University of Pittsburgh and Carnegie Mellon University.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: locationTeam2City
Context triple: [1989 Patrick Division Finals, locationTeam2City, Pittsburgh]
  • A. cityTeam2 chosen
    Indicates that a team is based in, represents, or is associated with a particular city.
  • B. locationTeam2Home
    Indicates that the specified location serves as the home venue or home ground for the second team involved in the context.
  • C. stateTeam2
    Indicates that a second team is associated with, represents, or belongs to a particular state or region.
  • D. homeVenueTeam2City
    Indicates that a second home venue team is based in or associated with a particular city.
  • E. hostTeamCity
    Indicates the city where the host team is based or where it plays its home events.
  • F. None of above.

Provenance (4 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_69d7bdf5e7cc8190be357278bc5ba3bb completed April 9, 2026, 2:55 p.m.
NER Named-entity recognition batch_69d9714208f881908f7f8a921362909a completed April 10, 2026, 9:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6af43f2188190b0e78f22dc6ba3f8 completed May 3, 2026, 2:13 a.m.
PD Predicate disambiguation batch_69d96fa3002881908000357b1f95a3ac completed April 10, 2026, 9:46 p.m.
Created at: April 9, 2026, 5:37 p.m.