Triple

T19110383
Position Surface form Disambiguated ID Type / Status
Subject Descent on Rochefort E467772 entity
Predicate location P40 FINISHED
Object Rochefort 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: Rochefort | Statement: [Descent on Rochefort, location, Rochefort]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Rochefort
Context triple: [Descent on Rochefort, location, Rochefort]
  • A. Rochefort chosen
    Rochefort is a historic French port town on the Atlantic coast known for its naval heritage and maritime museum sites.
  • B. Rochefort
    Rochefort is a town in the Walloon region of Belgium, known for its historic abbey and Trappist beer.
  • C. Rochefort
    Rochefort is a municipality in the canton of Neuchâtel in western Switzerland.
  • D. Rochefort-en-Terre
    Rochefort-en-Terre is a picturesque medieval village in Brittany, France, renowned for its well-preserved stone architecture and status as one of the country’s most beautiful villages.
  • E. Taillebourg
    Taillebourg is a commune in southwestern France known historically as the site of the 1242 Battle of Taillebourg between French royal forces and a coalition of rebellious nobles and English allies.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e393bafc81908e35a0eba7b807a6 completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:04 p.m.