Triple
T37284483
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Larsen's perfect game |
E925492
|
entity |
| Predicate | homeRunHitterInGame |
P14862
|
FINISHED |
| Object | Mickey Mantle |
—
|
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: Mickey Mantle | Statement: [Don Larsen's perfect game, homeRunHitterInGame, Mickey Mantle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeRunHitterInGame Context triple: [Don Larsen's perfect game, homeRunHitterInGame, Mickey Mantle]
-
A.
winningHomeRunHitter
Indicates the player who hit the home run that ultimately decided the victory for their team in a game.
-
B.
homeRunHitterNationalLeague
Indicates that the subject is a home run hitter who plays or played in the National League.
-
C.
firstHomeRunInGame
Indicates that the referenced home run is the first one hit by that player in that particular game.
-
D.
homeRuns
chosen
Indicates the number of home runs a player hits, or that a specific home run event occurs, in a baseball context.
-
E.
homeRunAllowedTo
Indicates that one entity (typically a pitcher or team) has allowed a home run to another entity (typically a batter or opposing team).
- 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.