Triple

T2778066
Position Surface form Disambiguated ID Type / Status
Subject Martin of Tours E61623 entity
Predicate deathPlace P21 FINISHED
Object Candes E61624 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: Candes | Statement: [Martin of Tours, deathPlace, Candes]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Candes
Context triple: [Martin of Tours, deathPlace, Candes]
  • A. Candes chosen
    Candes is a historic village in central France, best known as the place where Saint Martin of Tours died and now part of the commune Candes-Saint-Martin.
  • B. Arcot
    Arcot is a historic town in the Indian state of Tamil Nadu that served as an important political and military center, especially under the Nawabs of the Carnatic during the 18th century.
  • C. Kandel
    Kandel is a prominent mountain in Germany’s Black Forest region, known for its scenic views and outdoor recreation opportunities.
  • D. Coddington
    Coddington is an English-origin surname borne by various notable individuals, including early American colonial figures.
  • E. Brewster
    Brewster is the given name of Brewster Kahle, an American computer engineer and digital librarian best known as the founder of the Internet Archive.
  • 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_69ab4b7e43c48190997b8fc8fb1663ab completed March 6, 2026, 9:47 p.m.
NER Named-entity recognition batch_69abdd83c5fc8190936b971d5577d3f9 completed March 7, 2026, 8:10 a.m.
NED1 Entity disambiguation (via context triple) batch_69afc05cf84881908e771471dbda4c8d completed March 10, 2026, 6:55 a.m.
Created at: March 6, 2026, 9:57 p.m.