Triple
T24353731
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Josep Irla |
E613862
|
entity |
| Predicate | preservedInstitution |
P2249
|
FINISHED |
| Object | Generalitat of Catalonia |
—
|
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: Generalitat of Catalonia | Statement: [Josep Irla, preservedInstitution, Generalitat of Catalonia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: preservedInstitution Context triple: [Josep Irla, preservedInstitution, Generalitat of Catalonia]
-
A.
contributingInstitution
Indicates that an institution has provided or supplied content, resources, or support to a collection, project, or record.
-
B.
preservedAt
chosen
Indicates that something is kept, maintained, or conserved in a particular place or context.
-
C.
holdingInstitution
Indicates that one entity serves as the institution that holds, houses, or maintains custody of another entity (such as an item, collection, or resource).
-
D.
preservedAsPartOf
Indicates that something has been kept, maintained, or conserved within a larger whole of which it forms a component or subset.
-
E.
maintainedInstitution
Indicates that one entity is responsible for operating, supporting, or keeping another institution in working order over time.
- 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_69e2d7ddd29481909e7f539a6072bd71 |
completed | April 18, 2026, 1:01 a.m. |
| NER | Named-entity recognition | batch_69f2934732908190a50e69f492a5dc7a |
completed | April 29, 2026, 11:24 p.m. |
| PD | Predicate disambiguation | batch_69f287bb1b2c81909c2e7fcc392ad143 |
completed | April 29, 2026, 10:35 p.m. |
Created at: April 18, 2026, 1:59 a.m.