Triple
T30351094
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | canton of Saint-Quentin-2 |
E771991
|
entity |
| Predicate | isSeatPartlyIn |
P169084
|
FINISHED |
| Object | city of Saint-Quentin |
—
|
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: city of Saint-Quentin | Statement: [canton of Saint-Quentin-2, isSeatPartlyIn, city of Saint-Quentin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isSeatPartlyIn Context triple: [canton of Saint-Quentin-2, isSeatPartlyIn, city of Saint-Quentin]
-
A.
isSeatWithin
Indicates that one seat is located inside the spatial bounds or interior area defined by another object or region.
-
B.
seatSometimesLocatedIn
Indicates that the usual or primary seat of something is only occasionally or intermittently located within a given place or container.
-
C.
hasSeatAt
Indicates that an entity occupies or holds a place, position, or membership within a specific group, body, or location.
-
D.
seatIs
Indicates that one entity functions as the seat or seating position of another entity.
-
E.
hasSeat
Indicates that one entity possesses, provides, or includes a seat for another entity.
- F. None of above. chosen
Provenance (4 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_69f2248b9a208190bc3e6804acd5afd6 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f6823af4a4819095c725800c2be63e |
completed | May 2, 2026, 11:01 p.m. |
| PD | Predicate disambiguation | batch_69f678d019fc8190913662cd2f87b857 |
completed | May 2, 2026, 10:21 p.m. |
| PDg | Predicate description generation | batch_69f679496c188190ba585792f987a1f4 |
completed | May 2, 2026, 10:23 p.m. |
Created at: April 29, 2026, 7:56 p.m.