Triple
T3240769
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | How to Play Football |
E67959
|
entity |
| Predicate | usesNarrationBy |
P46114
|
FINISHED |
| Object | off-screen commentator |
—
|
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: off-screen commentator | Statement: [How to Play Football, usesNarrationBy, off-screen commentator]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: usesNarrationBy Context triple: [How to Play Football, usesNarrationBy, off-screen commentator]
-
A.
hasNarration
chosen
Indicates that an entity provides spoken or written commentary or storytelling for another entity, such as a work, event, or scene.
-
B.
narratorOf
Indicates that one entity serves as the narrator or storytelling voice for another entity, such as a text, story, or media work.
-
C.
narratedTo
Indicates that one entity tells or recounts a story, event, or information directly to another entity as the audience.
-
D.
narratorType
Indicates the narrative perspective or role from which a story or account is being told.
-
E.
usesSampleOfSpeechBy
Indicates that one entity employs or incorporates a sample of speech produced by another entity.
- 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_69ad858d27348190abb61c280b4c86a9 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69adaef6430081909084589f6eea5c7e |
completed | March 8, 2026, 5:16 p.m. |
| PD | Predicate disambiguation | batch_69ada4159e0481908cbbdd750f5e08c7 |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:08 p.m.