Triple
T38079910
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UGA–GT rivalry |
E950821
|
entity |
| Predicate | fanTraditionsUGA |
P178070
|
FINISHED |
| Object | "To Hell with Georgia Tech" chant |
—
|
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: "To Hell with Georgia Tech" chant | Statement: [UGA–GT rivalry, fanTraditionsUGA, "To Hell with Georgia Tech" chant]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fanTraditionsUGA Context triple: [UGA–GT rivalry, fanTraditionsUGA, "To Hell with Georgia Tech" chant]
-
A.
fanTraditionContext
Indicates the cultural or situational context in which a fan-related tradition occurs or is practiced.
-
B.
mascotTradition
Indicates a relationship where a mascot is associated with a recurring custom, ritual, or practice that is traditionally performed or upheld.
-
C.
homeFieldTradition
Indicates a customary practice, ritual, or behavior that is characteristically performed by or associated with a team when playing at its own home venue.
-
D.
bearerSchoolTradition
chosen
Indicates that an entity upholds, practices, or represents a particular school tradition.
-
E.
recordOfFloridaStateBeforeGame
Indicates the win–loss record held by Florida State prior to the referenced game.
- 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.