Triple
T28541308
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NFL PrimeTime |
E722296
|
entity |
| Predicate | featuresCommentaryBy |
P40446
|
FINISHED |
| Object | Chris Berman |
—
|
NE NERFINISHED |
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: Chris Berman | Statement: [NFL PrimeTime, featuresCommentaryBy, Chris Berman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCommentaryBy Context triple: [NFL PrimeTime, featuresCommentaryBy, Chris Berman]
-
A.
featuresAuthor
chosen
Indicates that something includes or highlights a particular author as a primary associated contributor.
-
B.
hasCommentaryOn
Indicates that one entity provides commentary, explanation, or evaluative remarks about another entity.
-
C.
typeOfCommentary
Indicates that one piece of commentary is a specific kind or subtype of another, more general category of commentary.
-
D.
commentaryFocus
Indicates that an item of commentary is primarily directed toward or centered on a particular entity, topic, or aspect.
-
E.
metaCommentaryOn
Indicates that one piece of content provides commentary, reflection, or analysis about another piece of content, often discussing its form, structure, or status as a work rather than its subject matter.
- 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_69f01a5e42348190b1ffbca26e739c84 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69fe7eb4b8348190bb19d35766189ed4 |
completed | May 9, 2026, 12:24 a.m. |
| PD | Predicate disambiguation | batch_69fe7c35d2148190ab952e54feda1e76 |
completed | May 9, 2026, 12:13 a.m. |
Created at: April 28, 2026, 3:35 a.m.