Triple
T29266653
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clássico Vovô |
E741993
|
entity |
| Predicate | featuresRival |
P54987
|
FINISHED |
| Object | Fluminense supporters |
—
|
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: Fluminense supporters | Statement: [Clássico Vovô, featuresRival, Fluminense supporters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: featuresRival Context triple: [Clássico Vovô, featuresRival, Fluminense supporters]
-
A.
rivalryFeature
Indicates a competitive or adversarial relationship between entities, often characterized by ongoing opposition or comparison.
-
B.
featuresOpponentType
chosen
Indicates that an entity involves, includes, or is associated with an opponent of a specified type within a competitive or adversarial context.
-
C.
featuresCompetitionIn
Indicates that something includes or presents a particular competition as part of its content or structure.
-
D.
featuresDemon
Indicates that an entity includes, depicts, or prominently involves a demon.
-
E.
featuresRiseOf
Indicates that something includes or portrays the emergence or increasing prominence of someone or something.
- 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_69f0912065c08190bddd23e20e8ef18e |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69ff46afe7e481908f2862ed11c88db2 |
completed | May 9, 2026, 2:37 p.m. |
| PD | Predicate disambiguation | batch_69ff45e9151881909c444a655e852165 |
completed | May 9, 2026, 2:34 p.m. |
Created at: April 28, 2026, 12:45 p.m.