Triple
T11761616
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1998 Rose Bowl |
E279669
|
entity |
| Predicate | washingtonStateSeasonRecordAfterGame |
P21379
|
FINISHED |
| Object | 10–2 |
—
|
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: 10–2 | Statement: [1998 Rose Bowl, washingtonStateSeasonRecordAfterGame, 10–2]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: washingtonStateSeasonRecordAfterGame Context triple: [1998 Rose Bowl, washingtonStateSeasonRecordAfterGame, 10–2]
-
A.
homeLeagueRecordAfterGame
Indicates the updated performance record of a team in its home league immediately following a specific game.
-
B.
postseasonWinLossRecord
Indicates the win–loss outcome record a team or individual has accumulated in postseason or playoff competition.
-
C.
seasonRecord
chosen
Indicates the overall performance or results an entity achieved over the course of a specific season (e.g., wins, losses, or comparable outcome metrics).
-
D.
winningTeamLeagueRecordEnteringGame
Indicates the win-loss (and possibly tie) record that the winning team had in its league before the game was played.
-
E.
seasonRecordWins
Indicates the number of games a team has won during a specific season.
- 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_69d6ab01d2688190ad8ed6bda487eaa5 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a52386708190b744746a2db37495 |
completed | April 10, 2026, 7:22 a.m. |
| PD | Predicate disambiguation | batch_69d88a829fe481909cc5431de7d6058e |
completed | April 10, 2026, 5:28 a.m. |
Created at: April 8, 2026, 9:41 p.m.