Triple

T10148577
Position Surface form Disambiguated ID Type / Status
Subject Nelly Roussel E231771 entity
Predicate familyName P18 FINISHED
Object Roussel E45966 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: Roussel | Statement: [Nelly Roussel, familyName, Roussel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Roussel
Context triple: [Nelly Roussel, familyName, Roussel]
  • A. Roussel chosen
    Roussel is a surname of French origin, often used as an alternative spelling of Russell.
  • B. Rousselot
    Rousselot is a French surname borne by various notable figures, including acclaimed cinematographer Philippe Rousselot.
  • C. Rabaut Saint-Étienne
    Rabaut Saint-Étienne was an 18th-century French Protestant pastor and revolutionary politician who played a significant role in advocating religious tolerance during the French Revolution.
  • D. Charpentier
    Charpentier is a French surname borne by various notable individuals across fields such as science, arts, and politics.
  • E. Clairmarais
    Clairmarais is a small commune in northern France known for its marshlands and canals, situated near the town of Saint-Omer.
  • 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_69ca848364f881908a24366a6feec1db completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cdec024da481908b8170fcf3b18e67 completed April 2, 2026, 4:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69d3175fa0c0819088d372f534f9447e completed April 6, 2026, 2:15 a.m.
Created at: March 30, 2026, 9:08 p.m.