Triple
T38366185
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Esporte Clube Vitória |
E892447
|
entity |
| Predicate | derbyCity |
P93359
|
FINISHED |
| Object | Salvador |
—
|
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: Salvador | Statement: [Esporte Clube Vitória, derbyCity, Salvador]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: derbyCity Context triple: [Esporte Clube Vitória, derbyCity, Salvador]
-
A.
derby
Indicates a competitive match or contest, typically between closely linked or rival entities (such as teams from the same area or group).
-
B.
regionDerby
Indicates a competitive match or rivalry that takes place between teams or participants from the same geographic region.
-
C.
derbyFocus
Indicates that something is the main subject, theme, or point of attention within the context of a derby event or competition.
-
D.
isDerby
Indicates that a competition or match is a derby, typically involving teams or participants from the same locality or with a strong rivalry.
-
E.
isFromCityWithDerby
chosen
Indicates that an entity originates from a city that has a football (or sports) derby with another team from the same city.
- 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_69f76e47cb4c8190bdd92cd1db59c0c5 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fcc7a4d7f881908b43b960911b81e9 |
completed | May 7, 2026, 5:11 p.m. |
| PD | Predicate disambiguation | batch_69fcc589720c819089c8f500fea3c86a |
completed | May 7, 2026, 5:02 p.m. |
Created at: May 3, 2026, 4:31 p.m.