Triple
T2299597
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Super Bowl VIII |
E51697
|
entity |
| Predicate | scoringSummaryFirstQuarter |
P38578
|
FINISHED |
| Object | MIA – Larry Csonka 5-yard run (Garo Yepremian kick) |
—
|
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: MIA – Larry Csonka 5-yard run (Garo Yepremian kick) | Statement: [Super Bowl VIII, scoringSummaryFirstQuarter, MIA – Larry Csonka 5-yard run (Garo Yepremian kick)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: scoringSummaryFirstQuarter Context triple: [Super Bowl VIII, scoringSummaryFirstQuarter, MIA – Larry Csonka 5-yard run (Garo Yepremian kick)]
-
A.
quarterScores
Indicates the scores achieved in each quarter of a game, match, or period-based event.
-
B.
opponentPointsAfterThreeQuarters
Indicates the number of points the opposing team has scored by the end of the third quarter of a game.
-
C.
GiantsPointsByQuarter
Indicates the number of points the Giants scored in each quarter of a game.
-
D.
RavensPointsByQuarter
Indicates the number of points the Ravens scored in each quarter of a game.
-
E.
targetScoreAfterThreeQuarters
Indicates the score that a target entity has accumulated by the end of the third quarter of a game or timed event.
- F. None of above. chosen
Provenance (4 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_69a88b0a9f248190bcff941463d8f65a |
completed | March 4, 2026, 7:42 p.m. |
| NER | Named-entity recognition | batch_69abcbabf01081908db3b42bc7c60444 |
completed | March 7, 2026, 6:54 a.m. |
| PD | Predicate disambiguation | batch_69abc58ad33c8190b8d68af41b6f5e07 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abcbab15488190bc8d2345f9d9f2bd |
completed | March 7, 2026, 6:54 a.m. |
Created at: March 4, 2026, 7:49 p.m.