Triple
T3435897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2008 Oregon–Oregon State football game |
E72449
|
entity |
| Predicate | awayRankingPreGame |
P42522
|
FINISHED |
| Object | Oregon No. 19 in AP Poll |
—
|
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: Oregon No. 19 in AP Poll | Statement: [2008 Oregon–Oregon State football game, awayRankingPreGame, Oregon No. 19 in AP Poll]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: awayRankingPreGame Context triple: [2008 Oregon–Oregon State football game, awayRankingPreGame, Oregon No. 19 in AP Poll]
-
A.
rankAtOpening
chosen
Indicates the position or level an entity holds within an ordered ranking at the initial or starting point of a specified period or event.
-
B.
formerRanking
Indicates that an entity previously held a particular rank or position but no longer does so.
-
C.
seriesScoreBeforeGame
Indicates the cumulative score or standing in a series between competitors as it existed prior to a specific game being played.
-
D.
tieToRankings
Indicates a relationship where something is linked or associated with a specific set of rankings or a ranking system.
-
E.
losingTeamRecordEnteringGame
Indicates that the team’s win-loss record prior to the game was a losing record (more losses than wins) entering that specific 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_69ad85af50288190a854b76653deee6f |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb9f2e4b4819085336fb539daf3c7 |
completed | March 8, 2026, 6:03 p.m. |
| PD | Predicate disambiguation | batch_69adae00ad588190bef24373b58a2e1a |
completed | March 8, 2026, 5:12 p.m. |
Created at: March 8, 2026, 3:16 p.m.