Triple
T38079809
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Georgia–Georgia Tech football rivalry |
E950819
|
entity |
| Predicate | fanBaseNicknameForSeries |
P23575
|
FINISHED |
| Object | Clean, Old-Fashioned Hate |
—
|
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: Clean, Old-Fashioned Hate | Statement: [Georgia–Georgia Tech football rivalry, fanBaseNicknameForSeries, Clean, Old-Fashioned Hate]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: fanBaseNicknameForSeries Context triple: [Georgia–Georgia Tech football rivalry, fanBaseNicknameForSeries, Clean, Old-Fashioned Hate]
-
A.
fanBaseName
Indicates the name by which the collective group of fans of a particular person, group, or entity is known.
-
B.
series1Nickname
Indicates that one entity is used as a nickname or informal alternative name for another entity within the context of a first series.
-
C.
teamNicknamedAfter
Indicates that a team is commonly referred to by a nickname derived from or inspired by another entity.
-
D.
teamNickname
Indicates the commonly used informal or symbolic name by which a team is known.
-
E.
fandomNickname
chosen
Indicates that one entity is the nickname used by fans to refer to another entity (such as a person, group, or work).
- 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.