Triple
T6553589
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doug Harvey |
E152387
|
entity |
| Predicate | yearsActiveAsUmpire |
P71768
|
FINISHED |
| Object | 1962–1992 |
—
|
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: 1962–1992 | Statement: [Doug Harvey, yearsActiveAsUmpire, 1962–1992]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: yearsActiveAsUmpire Context triple: [Doug Harvey, yearsActiveAsUmpire, 1962–1992]
-
A.
umpireDebutYear
Indicates the year in which an individual first began serving as an umpire, typically in an official or professional capacity.
-
B.
numberOfOffFieldUmpires
Indicates the count of umpires assigned to officiate a game from positions off the field of play.
-
C.
numberOfMLBGamesUmpired
Indicates the total count of Major League Baseball games that a given umpire has officiated.
-
D.
umpires
Indicates that an entity serves as the umpire overseeing, judging, or officiating an event, activity, or interaction involving another entity.
-
E.
umpiresProvidedBy
Indicates that one entity supplies or assigns umpires to officiate for another entity or 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_69c688058d6881908c19b309cc55dbfa |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6c1b15d3481908ae66e3d7564b352 |
completed | March 27, 2026, 5:43 p.m. |
| PD | Predicate disambiguation | batch_69c6acf6d4148190914b19e9affd8c76 |
completed | March 27, 2026, 4:14 p.m. |
| PDg | Predicate description generation | batch_69c6c1b007148190b5164d6d09584cdf |
completed | March 27, 2026, 5:43 p.m. |
Created at: March 27, 2026, 1:51 p.m.