Triple
T10336495
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Side (Pittsburgh) |
E243020
|
entity |
| Predicate | hasSportsTeamVenue |
P14457
|
FINISHED |
| Object | Pittsburgh Steelers home stadium |
—
|
LITERAL 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: Pittsburgh Steelers home stadium | Statement: [North Side (Pittsburgh), hasSportsTeamVenue, Pittsburgh Steelers home stadium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSportsTeamVenue Context triple: [North Side (Pittsburgh), hasSportsTeamVenue, Pittsburgh Steelers home stadium]
-
A.
hasSportsTeamVenueFor
chosen
Indicates that a venue serves as the home or hosting location for a particular sports team.
-
B.
hasProfessionalSportsVenue
Indicates that one entity possesses or hosts a venue specifically used for professional sports events.
-
C.
sportsVenueLocatedIn
Indicates that a sports venue is geographically situated within a specified location or administrative area.
-
D.
ownsSportsVenue
Indicates that one entity possesses legal ownership or controlling property rights over a sports venue used for athletic or sporting events.
-
E.
hasTeamStadium
Indicates that a sports team is associated with or plays its home games at a particular stadium.
- F. None of above.
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_69d381af787481908bc401325c760a88 |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e91fdb2081909866c6ecf417d75a |
completed | April 7, 2026, 11:23 a.m. |
| PD | Predicate disambiguation | batch_69d4df9dc3208190bf1bd106f44f6202 |
completed | April 7, 2026, 10:42 a.m. |
Created at: April 6, 2026, 11:54 a.m.