Triple

T11902102
Position Surface form Disambiguated ID Type / Status
Subject A3 autoroute E283176 entity
Predicate passesNear P416 FINISHED
Object Bondy E613622 NE FINISHED

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: Bondy | Statement: [A3 autoroute, passesNear, Bondy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bondy
Context triple: [A3 autoroute, passesNear, Bondy]
  • A. Bondy chosen
    Bondy is a suburban commune in the northeastern outskirts of Paris, France, served by regional rail and other public transport links into the capital.
  • B. Bondojito
    Bondojito is a station on Mexico City’s Metro system, serving passengers on Line 4 in the northern part of the city.
  • C. Bedjond
    Bedjond is a dialect of the Sara language spoken by communities in southern Chad.
  • D. Bondye
    Bondye is the supreme, transcendent creator god in Haitian Vodou, regarded as the distant but all-powerful source of the universe and all spiritual forces.
  • E. Bonderman
    Bonderman is a surname most prominently associated with American billionaire investor and private equity pioneer David Bonderman.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

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_69d6ab2c07e88190ba13b0d21fd6cf33 completed April 8, 2026, 7:23 p.m.
NER Named-entity recognition batch_69d8dd1792648190853f15fbf217eebd completed April 10, 2026, 11:20 a.m.
NED1 Entity disambiguation (via context triple) batch_69f4183d29b081908cfbf4d91a365681 completed May 1, 2026, 3:04 a.m.
Created at: April 8, 2026, 9:44 p.m.