Triple
T37284482
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Don Larsen's perfect game |
E925492
|
entity |
| Predicate | notableBatterHomeTeam |
P7087
|
FINISHED |
| Object | Mickey Mantle |
E11882
|
NE 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: Mickey Mantle | Statement: [Don Larsen's perfect game, notableBatterHomeTeam, Mickey Mantle]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableBatterHomeTeam Context triple: [Don Larsen's perfect game, notableBatterHomeTeam, Mickey Mantle]
-
A.
notableBatter
chosen
Indicates that the subject is a batter who is particularly prominent, distinguished, or noteworthy in the context of batting.
-
B.
homeRunsNotedFor
Indicates that an entity is recognized or recorded specifically for its home runs.
-
C.
notableShortstop
Indicates that the subject is recognized as a distinguished or prominent shortstop in baseball.
-
D.
notableCatcher
Indicates that the person is recognized as a prominent or distinguished catcher, typically in a sporting or professional context.
-
E.
homeRunDerbyParticipant
Indicates that an entity takes part as a competitor in a Home Run Derby event.
- F. None of above.
Provenance (4 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_6a037c8efcd4819088c2aeead65d93df |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a406cccddc4819089cc15a8baf722f0 |
completed | June 28, 2026, 12:37 a.m. |
| PD | Predicate disambiguation | batch_6a037a11efc08190bb7cacc1325b4dc6 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:16 p.m.