Triple
T554184
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thursday Night Football |
E11905
|
entity |
| Predicate | featuresCompetition |
P14365
|
FINISHED |
| Object | NFL teams |
—
|
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: NFL teams | Statement: [Thursday Night Football, featuresCompetition, NFL teams]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresCompetition Context triple: [Thursday Night Football, featuresCompetition, NFL teams]
-
A.
featuredCompetition
chosen
Indicates that a particular competition is highlighted or given special prominence relative to others.
-
B.
featuresEvent
Indicates that an entity includes, presents, or highlights a particular event as part of its content or offering.
-
C.
sportFocus
Indicates that one entity has a primary emphasis, specialization, or concentration on a particular sport represented by the other entity.
-
D.
competitionSurface
Indicates the type of surface or medium on which a competition or contest takes place.
-
E.
globalCompetition
Indicates a competitive relationship or rivalry that occurs between entities operating across multiple countries or on a worldwide scale.
- 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_69a4932941d08190815efd422f0b4ca7 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4991c524481908b2bb88c4feabec6 |
completed | March 1, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69a494bc1f8c8190904356f3a8e801de |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:32 p.m.