Triple
T24360613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Subsecretaría de Pesca y Acuicultura de Chile |
E614044
|
entity |
| Predicate | nombreCorto |
P125556
|
FINISHED |
| Object | Subpesca |
—
|
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: Subpesca | Statement: [Subsecretaría de Pesca y Acuicultura de Chile, nombreCorto, Subpesca]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nombreCorto Context triple: [Subsecretaría de Pesca y Acuicultura de Chile, nombreCorto, Subpesca]
-
A.
isShortName
chosen
Indicates that one name is an abbreviated or shorter form of another name.
-
B.
bearerShortName
Indicates that an entity serves as the short or abbreviated name used to identify the bearer in the context of a relationship or action.
-
C.
shortDesignation
Indicates that one entity serves as a brief or abbreviated designation (such as a short name, code, or label) for another entity.
-
D.
shortNameInJapanese
Indicates that an entity has a specific abbreviated or shorter form of its name expressed in the Japanese language.
-
E.
shortFormType
Indicates that one entity is a shortened, abbreviated, or otherwise condensed form or variant of another entity.
- 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_69e2d7dfe7f08190b7a1f3a36483ab05 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f29383ccb88190a4752fe7ccd93fd5 |
completed | April 29, 2026, 11:25 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 2 a.m.