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    Indicates that something in the vicinity previously had a particular use or function that is no longer current.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.