Triple
T33903881
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guilherandaises |
E869126
|
entity |
| Predicate | hasLocalUsage |
P184896
|
FINISHED |
| Object | Ardèche department |
—
|
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: Ardèche department | Statement: [Guilherandaises, hasLocalUsage, Ardèche department]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasLocalUsage Context triple: [Guilherandaises, hasLocalUsage, Ardèche department]
-
A.
hasLocalUnit
Indicates that an entity possesses or is associated with a subordinate organizational unit operating in a specific local area or region.
-
B.
localUse
chosen
Indicates that something is used, applied, or consumed within a specific local area, context, or jurisdiction rather than more broadly or globally.
-
C.
hasLocalSupport
Indicates that an entity receives backing, endorsement, or assistance from people or organizations within its immediate geographic or community area.
-
D.
hasUsageLevel
Indicates the degree or intensity with which something is used or utilized.
-
E.
isLocalTo
Indicates that one entity is geographically or contextually situated near, or within the same local area or scope as, 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_69f34997703c8190866b1d404bce531f |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69feb8e856d48190aa34ad8ee8376e1c |
completed | May 9, 2026, 4:32 a.m. |
| PD | Predicate disambiguation | batch_69feb82a2b6c8190a473cc25976897be |
completed | May 9, 2026, 4:29 a.m. |
Created at: May 1, 2026, 1:48 a.m.