Triple
T25542952
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al Downing |
E640218
|
entity |
| Predicate | ballparkOf715thHomeRun |
P132300
|
FINISHED |
| Object | Atlanta–Fulton County Stadium |
—
|
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: Atlanta–Fulton County Stadium | Statement: [Al Downing, ballparkOf715thHomeRun, Atlanta–Fulton County Stadium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ballparkOf715thHomeRun Context triple: [Al Downing, ballparkOf715thHomeRun, Atlanta–Fulton County Stadium]
-
A.
gameDateOfFamousHomeRun
Indicates the specific date on which a particular famous home run was hit in a game.
-
B.
homeRunDerbyVenue
Indicates the venue or location where a home run derby event takes place.
-
C.
ballparkLocatedOn
Indicates that a ballpark is situated on or directly associated with a specific street, road, or thoroughfare.
-
D.
ballparkGame1
chosen
Indicates a relationship where a specific ballpark is the venue hosting a particular game or sporting event.
-
E.
opponentBatterInFamousHomeRun
Indicates that the subject was the opposing batter involved in a specific, well-known home run event.
- 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_69e75dbfff7081909b0aa779d48321d2 |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f895e458819081cf031b70d20e56 |
completed | May 2, 2026, 1:13 p.m. |
| PD | Predicate disambiguation | batch_69f468421ba08190880eac99135e5970 |
completed | May 1, 2026, 8:45 a.m. |
Created at: April 21, 2026, 3:27 p.m.