Triple
T10702125
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bills Mafia |
E252301
|
entity |
| Predicate | rivalFanBaseOf |
P53223
|
FINISHED |
| Object | New England Patriots fans |
—
|
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: New England Patriots fans | Statement: [Bills Mafia, rivalFanBaseOf, New England Patriots fans]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: rivalFanBaseOf Context triple: [Bills Mafia, rivalFanBaseOf, New England Patriots fans]
-
A.
hasFanBaseRivalry
chosen
Indicates a competitive or antagonistic relationship between the fan bases of two entities.
-
B.
rivalOf
Indicates a relationship in which two entities compete against or oppose each other, often seeking advantage in the same domain or objective.
-
C.
rivalTeam
Indicates that one team is in a competitive or adversarial relationship with another team, often vying for superiority or dominance.
-
D.
associatedRivalry
Indicates a relationship where one entity is linked to another as its rival, competitor, or opposing counterpart.
-
E.
hasFanBaseFrom
Indicates that an entity has a significant group of supporters or followers originating from a specified place, group, or source.
- 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_69d6aa5cbabc8190973e683950d89faf |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6fd8c835c8190bf1a67ee94195926 |
completed | April 9, 2026, 1:14 a.m. |
| PD | Predicate disambiguation | batch_69d6dd8ea6408190a800f9cb57372189 |
completed | April 8, 2026, 10:58 p.m. |
Created at: April 8, 2026, 9:12 p.m.