Triple
T1501844
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Al Michaels |
E33813
|
entity |
| Predicate | isBestKnownFor |
P22
|
FINISHED |
| Object | play-by-play commentary on NFL 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: play-by-play commentary on NFL games | Statement: [Al Michaels, isBestKnownFor, play-by-play commentary on NFL games]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isBestKnownFor Context triple: [Al Michaels, isBestKnownFor, play-by-play commentary on NFL games]
-
A.
alsoKnownFor
Indicates that an entity is additionally recognized or noted for another work, role, achievement, or characteristic beyond its primary association.
-
B.
isMostProminentIn
Indicates that an entity stands out as the most notable, influential, or dominant among comparable entities within a specified context or domain.
-
C.
notableFor
chosen
Indicates that an entity is especially recognized or distinguished for a particular quality, achievement, characteristic, or role.
-
D.
notableFact
Indicates that there exists a particularly significant or noteworthy fact or piece of information associated with the subject.
-
E.
famousForEvent
Indicates that an entity is widely known or recognized specifically because of a particular event.
- 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_69a885f352a4819099b24ff15489dede |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a90584b8b881908e112c7e59163812 |
completed | March 5, 2026, 4:24 a.m. |
| PD | Predicate disambiguation | batch_69a88727ce48819089b482cdc25453d1 |
completed | March 4, 2026, 7:25 p.m. |
Created at: March 4, 2026, 7:24 p.m.