Triple
T1192587
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl IV |
E25394
|
entity |
| Predicate | pointSpreadMargin |
P2628
|
FINISHED |
| Object | Vikings by 12 points |
—
|
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: Vikings by 12 points | Statement: [Super Bowl IV, pointSpreadMargin, Vikings by 12 points]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: pointSpreadMargin Context triple: [Super Bowl IV, pointSpreadMargin, Vikings by 12 points]
-
A.
pointSpreadFavorite
chosen
Indicates which competitor or team is favored in a point spread betting line and by how many points they are expected to win.
-
B.
JetsScore
Indicates that the team named Jets scores a certain number of points in a game or event.
-
C.
homeFieldAdvantage
Indicates that one participant benefits from playing or operating in a familiar or home environment, gaining an advantage over the opponent.
-
D.
halftimeScore
Indicates the score or result of a game or match at the halfway point (halftime).
-
E.
totalPointsScored
Indicates the total number of points accumulated or scored by an entity over a defined period, event, or context.
- 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_69a49427d98881908646d6c63b8cea1e |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bd761ef08190b431b80f326d1ab2 |
completed | March 1, 2026, 10:28 p.m. |
| PD | Predicate disambiguation | batch_69a4bb5bacc481909e8dfd5215e4711a |
completed | March 1, 2026, 10:19 p.m. |
Created at: March 1, 2026, 7:45 p.m.