Triple
T26449643
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rue de Richelieu |
E665308
|
entity |
| Predicate | hasNearbyPassage |
P181297
|
FINISHED |
| Object | Galerie Vivienne |
—
|
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: Galerie Vivienne | Statement: [Rue de Richelieu, hasNearbyPassage, Galerie Vivienne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyPassage Context triple: [Rue de Richelieu, hasNearbyPassage, Galerie Vivienne]
-
A.
hasNearbyPass
Indicates that an entity has at least one pass (e.g., transit or access pass) available within a short or locally defined distance from it.
-
B.
hasNearbyCommon
Indicates that two entities share at least one common element, feature, or connection that is located within a specified nearby distance or vicinity.
-
C.
hasNearbyAccess
Indicates that one entity has convenient, close-proximity access to another resource, service, or location.
-
D.
hasFormerUseNearby
Indicates that something in the vicinity previously had a particular use or function that is no longer current.
-
E.
hasNearbyGate
Indicates that one entity has a gate located in close physical proximity to it.
- 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_69ee883d5040819097dd154643005230 |
completed | April 26, 2026, 9:48 p.m. |
| NER | Named-entity recognition | batch_69f7688dd3d08190ad13d0e780570a1c |
completed | May 3, 2026, 3:23 p.m. |
| PD | Predicate disambiguation | batch_69f767fcf2f881908bacc7bfc38e68a5 |
completed | May 3, 2026, 3:21 p.m. |
| PDg | Predicate description generation | batch_69f7688cea58819098bdfd7c80df7634 |
completed | May 3, 2026, 3:23 p.m. |
Created at: April 27, 2026, 12:04 a.m.