Triple
T32969156
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Feria de Cali |
E843459
|
entity |
| Predicate | cityNickNameReinforced |
P74834
|
FINISHED |
| Object | Capital de la Salsa |
—
|
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: Capital de la Salsa | Statement: [Feria de Cali, cityNickNameReinforced, Capital de la Salsa]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cityNickNameReinforced Context triple: [Feria de Cali, cityNickNameReinforced, Capital de la Salsa]
-
A.
cityNickname
Indicates that one entity is commonly used as an informal or alternative name for a city.
-
B.
cityNicknameAssociation
chosen
Indicates an associative relationship where a particular nickname is used to refer to or characterize a specific city.
-
C.
cityNickNameForFanBase
Indicates that a particular nickname is used by fans to refer to a city or its fan base.
-
D.
isInCityNicknamed
Indicates that one entity is located in a city that is known by a particular nickname.
-
E.
cityNicknameOrigin
Indicates the relationship between a city and the source, reason, or inspiration from which its nickname is derived.
- 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_69f3494b9fc48190bb61c955ba471275 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f6d1a81e348190a37ae574e7174449 |
completed | May 3, 2026, 4:40 a.m. |
| PD | Predicate disambiguation | batch_69f6cfe5f93c8190995c53dbbe380a32 |
completed | May 3, 2026, 4:32 a.m. |
Created at: May 1, 2026, 1:21 a.m.