Triple
T8521817
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rutgers–Lafayette football rivalry |
E201709
|
entity |
| Predicate | typicalGameSite |
P12966
|
FINISHED |
| Object | home stadium of Rutgers University |
—
|
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: home stadium of Rutgers University | Statement: [Rutgers–Lafayette football rivalry, typicalGameSite, home stadium of Rutgers University]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalGameSite Context triple: [Rutgers–Lafayette football rivalry, typicalGameSite, home stadium of Rutgers University]
-
A.
gameSites
Indicates that one entity is associated with or hosts locations, platforms, or venues where games are played, accessed, or made available.
-
B.
typicalGameLocation
chosen
Indicates the usual or characteristic place where a game is played or takes place.
-
C.
gamingSpace
Indicates a relationship where a space, area, or environment is designated or used specifically for gaming activities.
-
D.
openingRoundGameSite
Indicates the location or venue where the opening round game of a competition or series is held.
-
E.
homeGamesVenueType
Indicates the type or category of venue where a team plays its home games.
- 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_69ca8321bb44819081b74df0b710276d |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe62a490481908ee0ad4ba9a94682 |
completed | March 31, 2026, 3:20 p.m. |
| PD | Predicate disambiguation | batch_69cbd10f64b4819080859057c19e58f0 |
completed | March 31, 2026, 1:50 p.m. |
Created at: March 30, 2026, 6:16 p.m.