Triple
T38079864
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgia vs. Georgia Tech |
E950820
|
entity |
| Predicate | isCollegeFootballRivalryOf |
P74502
|
FINISHED |
| Object | University of Georgia |
—
|
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: University of Georgia | Statement: [Georgia vs. Georgia Tech, isCollegeFootballRivalryOf, University of Georgia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isCollegeFootballRivalryOf Context triple: [Georgia vs. Georgia Tech, isCollegeFootballRivalryOf, University of Georgia]
-
A.
nicknameOfRivalryBetween
Indicates that one entity is a nickname or informal title used to refer to a particular rivalry between other entities.
-
B.
isAFLLegacyRivalry
Indicates a historical or long-standing rivalry between two entities within the context of the AFL (Australian Football League).
-
C.
hasRivalryIn
Indicates that two entities are in a state of competition or opposition within a specific domain, context, or field.
-
D.
associatedRivalry
chosen
Indicates a relationship where one entity is linked to another as its rival, competitor, or opposing counterpart.
-
E.
rivalConferenceTeams
Indicates that the two teams compete in the same athletic conference and are considered rivals within that conference.
- 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_69f76f03a3608190a73fd6df87c792a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fc4748843c8190931432653be4890c |
completed | May 7, 2026, 8:03 a.m. |
| PD | Predicate disambiguation | batch_69fc45646ce481908caf292ff9f06e15 |
completed | May 7, 2026, 7:55 a.m. |
Created at: May 3, 2026, 4:21 p.m.