Triple
T32804421
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NFC Championship Game 2008 season vs. Arizona Cardinals |
E838981
|
entity |
| Predicate | eaglesFourthQuarterLead |
P84733
|
FINISHED |
| Object | 25–24 |
—
|
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: 25–24 | Statement: [NFC Championship Game 2008 season vs. Arizona Cardinals, eaglesFourthQuarterLead, 25–24]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eaglesFourthQuarterLead Context triple: [NFC Championship Game 2008 season vs. Arizona Cardinals, eaglesFourthQuarterLead, 25–24]
-
A.
eaglesComebackMargin
Indicates the point difference by which the Eagles overcame a deficit to win or tie a game.
-
B.
eaglesDeficitScore
chosen
Indicates the numerical amount by which the Eagles are trailing (their deficit) in a scoring context.
-
C.
EaglesPointsSecondHalf
Indicates the number of points the Eagles scored during the second half of a game.
-
D.
EaglesQuarterback
Indicates that the subject is a quarterback who plays for the Philadelphia Eagles football team.
-
E.
EaglesPointsFirstHalf
Indicates that the Eagles scored a certain number of points in the first half of a game.
- 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_69f3493d35208190b4351b4e85f2fa16 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6ce6d659881909ddcec1d2966e020 |
completed | May 3, 2026, 4:26 a.m. |
| PD | Predicate disambiguation | batch_69f6cc1667a48190b42684f6ec22dae9 |
completed | May 3, 2026, 4:16 a.m. |
Created at: May 1, 2026, 1:15 a.m.