Triple

T16392445
Position Surface form Disambiguated ID Type / Status
Subject Saint-Herblain E398086 entity
Predicate adjacentTo P224 FINISHED
Object Orvault E393201 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: Orvault | Statement: [Saint-Herblain, adjacentTo, Orvault]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Orvault
Context triple: [Saint-Herblain, adjacentTo, Orvault]
  • A. Orvault chosen
    Orvault is a suburban commune in western France, forming part of the metropolitan area of Nantes in the Loire-Atlantique department.
  • B. The Vault
    "The Vault" is an episode of the animated television series Adventure Time that delves into Princess Bubblegum’s past and the hidden memories of Finn’s previous life.
  • C. Keepit Dam
    Keepit Dam is a major water storage and irrigation dam located on the Namoi River in New South Wales, Australia.
  • D. Vaults
    Vaults is a British electronic pop trio known for their atmospheric, cinematic sound and emotive vocals.
  • E. Zoho Vault
    Zoho Vault is a cloud-based password manager and secure credential storage solution designed for individuals and teams to safely manage and share passwords and other sensitive data.
  • 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_69d87f2880b48190ae1a9673a3bbef80 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e326436ce881909f0f3899b8d931aa completed April 18, 2026, 6:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a003573c6d48190979201b9619c5103 completed May 10, 2026, 7:36 a.m.
Created at: April 10, 2026, 5:08 a.m.