Triple

T17969176
Position Surface form Disambiguated ID Type / Status
Subject Nicolas Jean-de-Dieu Soult E449288 entity
Predicate familyName P18 FINISHED
Object Soult 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: Soult | Statement: [Nicolas Jean-de-Dieu Soult, familyName, Soult]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soult
Context triple: [Nicolas Jean-de-Dieu Soult, familyName, Soult]
  • A. Soult chosen
    Soult is a French surname most famously associated with Nicolas Jean-de-Dieu Soult, a prominent marshal of France under Napoleon.
  • B. Manceau
    Manceau is the French term used to refer to an inhabitant or native of the city of Le Mans.
  • C. Sillian
    Sillian is a market town in the Austrian state of Tyrol, located near the Italian border in the eastern Alps.
  • D. Volkmer
    Volkmer is a surname most notably associated with Harold L. Volkmer, an American politician who served as a U.S. Representative from Missouri.
  • E. Reiner
    Reiner is a surname most prominently associated with American filmmaker and actor Rob Reiner and his father, comedian and director Carl Reiner.
  • 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_69d8b9f9927c8190a006110c8b996e61 completed April 10, 2026, 8:51 a.m.
NER Named-entity recognition batch_69e4b13b1b088190b7d71006b31e5cc3 completed April 19, 2026, 10:40 a.m.
Created at: April 10, 2026, 10:22 a.m.