Triple
T38678568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1997 Rose Bowl |
E943823
|
entity |
| Predicate | nextRoseBowl |
P191519
|
FINISHED |
| Object | 1998 Rose Bowl |
—
|
NE NERFINISHED |
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: 1998 Rose Bowl | Statement: [1997 Rose Bowl, nextRoseBowl, 1998 Rose Bowl]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nextRoseBowl Context triple: [1997 Rose Bowl, nextRoseBowl, 1998 Rose Bowl]
-
A.
nextOrangeBowl
Indicates that one entity is the next scheduled occurrence of the Orange Bowl game relative to a given reference point or event.
-
B.
nextNFLChampionshipGame
Indicates that one game is the immediately upcoming NFL championship game relative to a given reference time or schedule.
-
C.
nextSuperBowl
Indicates that one event is the immediately upcoming occurrence of the Super Bowl relative to a given reference point or time.
-
D.
nextFinals
Indicates that one event, match, or stage directly follows another as the subsequent or upcoming finals in a sequence.
-
E.
nextAFCChampionshipGame
Indicates the relationship where a given entity is the immediately upcoming AFC Championship Game in time.
- 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_69f76eec28708190b9c82a505fc278e0 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcdfbc71c481908ba7f87907b17782 |
completed | May 7, 2026, 6:53 p.m. |
| PD | Predicate disambiguation | batch_69fcdbe580b8819087f143596b2c79c0 |
completed | May 7, 2026, 6:37 p.m. |
| PDg | Predicate description generation | batch_69fcdfbafbf48190abe38ec0003a6419 |
completed | May 7, 2026, 6:53 p.m. |
Created at: May 3, 2026, 4:33 p.m.