Triple
T28480087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ley 2/1985 de Protección Civil |
E720667
|
entity |
| Predicate | tipoEmergencias |
P155803
|
FINISHED |
| Object | emergencias de protección civil de origen natural |
—
|
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: emergencias de protección civil de origen natural | Statement: [Ley 2/1985 de Protección Civil, tipoEmergencias, emergencias de protección civil de origen natural]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tipoEmergencias Context triple: [Ley 2/1985 de Protección Civil, tipoEmergencias, emergencias de protección civil de origen natural]
-
A.
typeOfEmergencyService
Indicates the specific category or kind of emergency service associated with or provided in a given situation.
-
B.
typeOfRescue
Indicates the specific method or category of rescue operation performed in a rescue event.
-
C.
emergencyAlertType
Indicates the specific category or kind of emergency associated with an alert.
-
D.
typeOfCrisis
Indicates the specific category or nature of a crisis that an entity is experiencing or associated with.
-
E.
typeOfDisaster
chosen
Indicates that one entity is classified as a specific kind or category of disaster in relation to 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_69f01a5983f48190b7c1b8857245a4f7 |
completed | April 28, 2026, 2:24 a.m. |
| NER | Named-entity recognition | batch_69f64ee8b3c08190a7efb9739393ca90 |
completed | May 2, 2026, 7:22 p.m. |
| PD | Predicate disambiguation | batch_69f64cb0d8008190912e1430cfaf92aa |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 28, 2026, 2:54 a.m.