Triple
T3585029
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Whitey Ford |
E75888
|
entity |
| Predicate | teamRecord |
P49500
|
FINISHED |
| Object | most career wins by a New York Yankees pitcher |
—
|
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: most career wins by a New York Yankees pitcher | Statement: [Whitey Ford, teamRecord, most career wins by a New York Yankees pitcher]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamRecord Context triple: [Whitey Ford, teamRecord, most career wins by a New York Yankees pitcher]
-
A.
seasonRecord
Indicates the overall performance or results an entity achieved over the course of a specific season (e.g., wins, losses, or comparable outcome metrics).
-
B.
NLTeamRegularSeasonRecord
Indicates the win–loss (and often tie) performance record of a National League baseball team over a regular season.
-
C.
ALTeamRegularSeasonRecord
Indicates the relationship that specifies a team's win–loss record during the American League regular season.
-
D.
teamAchievement
Indicates that a group of individuals collectively accomplished a shared goal or met a performance milestone.
-
E.
teamScoring
Indicates that a team achieves a score or points in a game, match, or competitive event.
- F. None of above. chosen
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_69ad85d6dc3c8190b491b79b83e25461 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc135ee3481908ef8dc41af632710 |
completed | March 8, 2026, 6:34 p.m. |
| PD | Predicate disambiguation | batch_69adb839b4e08190b1c0d611cccb11ae |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adb902e61c81908f10494f828e260f |
completed | March 8, 2026, 5:59 p.m. |
Created at: March 8, 2026, 3:22 p.m.