Triple
T15911023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bud Wilkinson |
E385846
|
entity |
| Predicate | unbeatenStreakLength |
P121028
|
FINISHED |
| Object | 47 games |
—
|
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: 47 games | Statement: [Bud Wilkinson, unbeatenStreakLength, 47 games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: unbeatenStreakLength Context triple: [Bud Wilkinson, unbeatenStreakLength, 47 games]
-
A.
unbeatenStreakYears
Indicates the number of consecutive years during which an entity has remained unbeaten or undefeated.
-
B.
longestUnbeatenStreak
Indicates the relationship where an entity holds the greatest continuous sequence of events (such as games or matches) without a loss compared to others.
-
C.
endedStreakOf
Indicates that one entity caused another entity's ongoing streak (such as a series of successes, events, or performances) to come to an end.
-
D.
defenderNationStreak
Indicates the sequence or run of consecutive events in which the same nation has acted as the defender.
-
E.
consecutiveGamesRecordHeldFrom
Indicates that one entity held the record for most consecutive games played starting from a specified point in time.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142ca3b208190946c3aa4c1e6087c |
completed | April 16, 2026, 8:12 p.m. |
| PDg | Predicate description generation | batch_69e17d48cc9c8190b03fd07ae2e9dfd8 |
completed | April 17, 2026, 12:22 a.m. |
Created at: April 10, 2026, 4:52 a.m.