Triple
T33331810
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Welser concession in Venezuela |
E853425
|
entity |
| Predicate | countryGrantedBy |
P191623
|
FINISHED |
| Object | Crown of Castile |
—
|
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: Crown of Castile | Statement: [Welser concession in Venezuela, countryGrantedBy, Crown of Castile]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryGrantedBy Context triple: [Welser concession in Venezuela, countryGrantedBy, Crown of Castile]
-
A.
countryOfPatronage
Indicates the country that officially supports, sponsors, or acts as a patron for a given entity or activity.
-
B.
granteeCountry
chosen
Indicates the country associated with the recipient (grantee) of a grant or award.
-
C.
countryRepresented
Indicates that one entity serves as the official representative (such as an athlete, diplomat, or delegate) of a specific country in a given context or event.
-
D.
repositoryCountry
Indicates the country in which a repository is located or maintained.
-
E.
countryAnnexedBy
Indicates that a country has been taken over and incorporated into the territory of another state through annexation.
- 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_69f34969614c81909cd99661b0902533 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a00a15604fc8190b1c280794960f3a4 |
completed | May 10, 2026, 3:16 p.m. |
| PD | Predicate disambiguation | batch_6a00a0f7e77881909ac85755ab0e6329 |
completed | May 10, 2026, 3:15 p.m. |
Created at: May 1, 2026, 1:34 a.m.