Triple
T25046026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1960 Pittsburgh Pirates season |
E627242
|
entity |
| Predicate | WorldSeriesGame4WinningPitcher |
P16640
|
FINISHED |
| Object | Vern Law |
—
|
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: Vern Law | Statement: [1960 Pittsburgh Pirates season, WorldSeriesGame4WinningPitcher, Vern Law]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: WorldSeriesGame4WinningPitcher Context triple: [1960 Pittsburgh Pirates season, WorldSeriesGame4WinningPitcher, Vern Law]
-
A.
game4WinningPitcher
chosen
Indicates the relationship between a specific game and the pitcher who was credited with the win in that game.
-
B.
game2WinningPitcher
Indicates that one entity is the pitcher who earned the win in the second game of a series or event for the other entity.
-
C.
winningGamePitcher
Indicates that the subject is the pitcher credited with the win in a particular baseball game.
-
D.
game5WinningPitcher
Indicates the pitcher who was credited with the win in game 5 of a series or event.
-
E.
game1WinningPitcher
Indicates that the subject is the pitcher credited with the win in game 1 of a series or 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_69e2ff2b4c80819087c916b2b16241b9 |
completed | April 18, 2026, 3:48 a.m. |
| NER | Named-entity recognition | batch_69f5ffc74fa481909b4fe24a9337f9eb |
completed | May 2, 2026, 1:44 p.m. |
| PD | Predicate disambiguation | batch_69f5f7f99dc08190afcfb3bc4dfbec1d |
completed | May 2, 2026, 1:11 p.m. |
Created at: April 18, 2026, 6:08 a.m.