Triple
T37146642
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Font-Romeu-Odeillo-Via |
E920257
|
entity |
| Predicate | hasSolarResearchFacility |
P15417
|
FINISHED |
| Object | Odeillo solar furnace |
—
|
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: Odeillo solar furnace | Statement: [Font-Romeu-Odeillo-Via, hasSolarResearchFacility, Odeillo solar furnace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasSolarResearchFacility Context triple: [Font-Romeu-Odeillo-Via, hasSolarResearchFacility, Odeillo solar furnace]
-
A.
hasResearchInfrastructure
chosen
Indicates that an entity possesses, controls, or provides access to facilities, equipment, or resources used to conduct research.
-
B.
hasResearchCentersIn
Indicates that an entity maintains or operates research centers located within a specified place or region.
-
C.
isResearchStructureFor
Indicates that one entity serves as a research-related structure, facility, or framework specifically intended for use by another entity.
-
D.
researchSite
Indicates that a location serves as a site where research or investigative studies are conducted or based.
-
E.
hasResearchCenters
Indicates that an entity possesses, hosts, or is associated with one or more research centers.
- 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_69f76e9f87c08190b4c8f7fafbd8345a |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fdbaa226708190b8ed96e93aad38de |
completed | May 8, 2026, 10:27 a.m. |
| PD | Predicate disambiguation | batch_69fdb58b07e48190837e00966de050d4 |
completed | May 8, 2026, 10:06 a.m. |
Created at: May 3, 2026, 4:15 p.m.