Triple
T34473242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Regency of Spain |
E884959
|
entity |
| Predicate | SpanishLabel |
P12773
|
FINISHED |
| Object | Regencia de España |
—
|
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: Regencia de España | Statement: [Regency of Spain, SpanishLabel, Regencia de España]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: SpanishLabel Context triple: [Regency of Spain, SpanishLabel, Regencia de España]
-
A.
SpanishObjective
Indicates that an entity is the target or goal of an action, relation, or expression specifically in the Spanish language.
-
B.
SpanishEditionURL
Indicates the web address where the Spanish-language edition or version of something can be accessed.
-
C.
SpanishStrength
Indicates a relationship where something or someone possesses strength, power, or intensity specifically associated with Spain or the Spanish context.
-
D.
hasSpanishMeaning
Indicates that one entity serves as the Spanish-language meaning or translation of another entity.
-
E.
hasNameInSpanish
chosen
Indicates that an entity is associated with a specific name expressed in the Spanish language.
- 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_69f349c880408190ade571c471ab154a |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f7199f91ec8190a4459f389a914cf0 |
completed | May 3, 2026, 9:47 a.m. |
| PD | Predicate disambiguation | batch_69f71824431081908d9685d2462ea242 |
completed | May 3, 2026, 9:40 a.m. |
Created at: May 1, 2026, 2:01 a.m.