Triple
T5164907
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Randy Johnson |
E116526
|
entity |
| Predicate | pitchedPerfectGame |
P31115
|
FINISHED |
| Object | 2004-05-18 |
—
|
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: 2004-05-18 | Statement: [Randy Johnson, pitchedPerfectGame, 2004-05-18]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pitchedPerfectGame Context triple: [Randy Johnson, pitchedPerfectGame, 2004-05-18]
-
A.
pitchedPerfectGameDate
chosen
Indicates the date on which a pitcher threw a perfect game.
-
B.
threwPerfectGame
Indicates that one entity (typically a pitcher) completed a game without allowing any opposing player to reach base, achieving a perfect game against another entity (typically a team).
-
C.
yearOfPerfectGame
Indicates the specific year in which a perfect game occurred or was achieved.
-
D.
pitchedShutoutIn
Indicates that an individual (typically a pitcher) completed a game in a particular event or season without allowing the opposing team to score any runs.
-
E.
game4WinningPitcher
Indicates the relationship between a specific game and the pitcher who was credited with the win in that game.
- 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_69bd445edb3881909b93b34d260717fc |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd792936d48190825da8826448c1da |
completed | March 20, 2026, 4:43 p.m. |
| PD | Predicate disambiguation | batch_69bd77b36c008190b91011a9fa52b3d2 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:44 p.m.