Triple

T11686387
Position Surface form Disambiguated ID Type / Status
Subject Le Blanc-Mesnil E277754 entity
Predicate nearbyCommune P3883 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: [Le Blanc-Mesnil, nearbyCommune, Bondy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bondy
Context triple: [Le Blanc-Mesnil, nearbyCommune, 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. Bedjond
    Bedjond is a dialect of the Sara language spoken by communities in southern Chad.
  • C. 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.
  • D. Bonderman
    Bonderman is a surname most prominently associated with American billionaire investor and private equity pioneer David Bonderman.
  • E. Bonda’
    Bonda’ is an alternative name for the Suwawa language, an Austronesian language spoken in parts of northern Sulawesi, Indonesia.
  • 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_69d6aafe02d881909900d54ad7d4af84 completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d8a4654be881909bd0256cf18e25de completed April 10, 2026, 7:19 a.m.
NED1 Entity disambiguation (via context triple) batch_69ef1433be908190b2ac887655a6c85a completed April 27, 2026, 7:45 a.m.
Created at: April 8, 2026, 9:40 p.m.