Triple
T37284465
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Larsen's perfect game |
E925492
|
entity |
| Predicate | baserunnersAllowedByDonLarsen |
P116560
|
FINISHED |
| Object | 0 |
—
|
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: 0 | Statement: [Don Larsen's perfect game, baserunnersAllowedByDonLarsen, 0]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: baserunnersAllowedByDonLarsen Context triple: [Don Larsen's perfect game, baserunnersAllowedByDonLarsen, 0]
-
A.
homeRunAllowedTo
Indicates that one entity (typically a pitcher or team) has allowed a home run to another entity (typically a batter or opposing team).
-
B.
pitcherWhoAllowedWalkOff
Indicates the pitcher who gave up the game-ending (walk-off) play that resulted in the opposing team’s immediate victory.
-
C.
perfectGameRunsAllowed
Indicates that in a perfect game, the number of runs allowed by the pitcher or team is recorded or constrained to a specific value (typically zero).
-
D.
perfectGameWalksAllowed
Indicates that in a so-called perfect game, the pitcher is allowed to issue one or more walks while still having the game classified under this relaxed perfect-game criterion.
-
E.
perfectGameHitsAllowed
chosen
Indicates the number of hits a pitcher allows while throwing a perfect 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_69f76eafe20c8190856d3b996a4c31a7 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69fb78cbef988190b8f79d946b46e6b2 |
completed | May 6, 2026, 5:22 p.m. |
| PD | Predicate disambiguation | batch_69fb5a9ac5a08190b24ef308963fc52b |
completed | May 6, 2026, 3:13 p.m. |
Created at: May 3, 2026, 4:16 p.m.