Triple
T36194847
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tampa Tarpons |
E1047092
|
entity |
| Predicate | sharesBallparkComplexWith |
P45314
|
FINISHED |
| Object | New York Yankees spring training |
—
|
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: New York Yankees spring training | Statement: [Tampa Tarpons, sharesBallparkComplexWith, New York Yankees spring training]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: sharesBallparkComplexWith Context triple: [Tampa Tarpons, sharesBallparkComplexWith, New York Yankees spring training]
-
A.
sharesBallparkWith
chosen
Indicates that two entities use or occupy the same ballpark as their home or primary venue.
-
B.
associatedWithBallpark
Indicates that an entity has a relationship or connection to a specific ballpark, such as location, operation, or affiliation.
-
C.
hasBallpark
Indicates that an entity possesses, is associated with, or includes a specific ballpark as part of its attributes or facilities.
-
D.
sharesStadiumWith
Indicates that two teams or organizations use the same stadium as their home or primary venue.
-
E.
ballpark
Indicates an approximate or rough estimation of a value, rather than an exact or precise figure.
- 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_69f76e3d4fbc81908c159c7beeb4ce00 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a008ac37dc081908d360574912f40ec |
completed | May 10, 2026, 1:40 p.m. |
| PD | Predicate disambiguation | batch_6a008a67d73881909855ab4cfca3c399 |
completed | May 10, 2026, 1:38 p.m. |
Created at: May 3, 2026, 4:08 p.m.