Triple
T28968517
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penn State–Michigan State football rivalry |
E732106
|
entity |
| Predicate | teamNicknamePennState |
P166070
|
FINISHED |
| Object | Nittany Lions |
—
|
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: Nittany Lions | Statement: [Penn State–Michigan State football rivalry, teamNicknamePennState, Nittany Lions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: teamNicknamePennState Context triple: [Penn State–Michigan State football rivalry, teamNicknamePennState, Nittany Lions]
-
A.
coachOhioStateFullName
Indicates that a person serves or served as a coach for the Ohio State team, with their full name specified.
-
B.
homeTeamUniversity
Indicates that a specified university serves as the home institution or host team in a given game, match, or sporting event.
-
C.
pennantTeam
Indicates that a team has won or represents the league or conference pennant for a given season or competition.
-
D.
villanovaTeamName
Indicates that an entity is the official team name associated with Villanova University.
-
E.
mostPennantsTeam
Indicates that the subject is the team that has won the greatest number of league pennants within a specified context or league.
- 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_69f043ee242c8190b063248b417c5a69 |
completed | April 28, 2026, 5:21 a.m. |
| NER | Named-entity recognition | batch_69f65c2ee360819096cf112e4bcde260 |
completed | May 2, 2026, 8:18 p.m. |
| PD | Predicate disambiguation | batch_69f659d02f1c8190831758ac52bb54e4 |
completed | May 2, 2026, 8:08 p.m. |
| PDg | Predicate description generation | batch_69f65b136b30819090cf59fb772f35f1 |
completed | May 2, 2026, 8:14 p.m. |
Created at: April 28, 2026, 8:53 a.m.