Triple

T20797149
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth of the Trinity E511940 entity
Predicate burialPlace P196 FINISHED
Object Carmel of Dijon 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: Carmel of Dijon | Statement: [Elizabeth of the Trinity, burialPlace, Carmel of Dijon]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Carmel of Dijon
Context triple: [Elizabeth of the Trinity, burialPlace, Carmel of Dijon]
  • A. Dijon Carmel chosen
    Dijon Carmel is a Discalced Carmelite monastery in Dijon, France, known as the convent where Saint Elizabeth of the Trinity lived and deepened her contemplative spiritual life.
  • B. La Roche-Bernard
    La Roche-Bernard is a small historic town in western France known for its picturesque port and cliffs overlooking the Vilaine River.
  • C. Bourg-Madame
    Bourg-Madame is a small French commune in the Pyrénées-Orientales department, situated on the border with Spain in the Cerdagne region.
  • D. Montlignon
    Montlignon is a small commune in the Val-d'Oise department in the Île-de-France region of northern France.
  • E. Marignier
    Marignier is a commune in the Haute-Savoie department of southeastern France, situated in the French Alps.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e0b4cc69f481908e98751e697b9df4 completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2ad6f0481909e0bab7119f10f9c completed April 21, 2026, 12:19 a.m.
Created at: April 16, 2026, 12:39 p.m.