Triple

T20810998
Position Surface form Disambiguated ID Type / Status
Subject Adeliza de Tosny E512299 entity
Predicate familyName P18 FINISHED
Object de Tosny
De Tosny is a Norman noble family name associated with several medieval aristocratic lineages in England and Normandy.
E1451760 NE FINISHED

How this triple was built (4 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: de Tosny | Statement: [Adeliza de Tosny, familyName, de Tosny]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: de Tosny
Context triple: [Adeliza de Tosny, familyName, de Tosny]
  • A. Nancoury
    Nancoury is an alternative name for the Nancowry language, an Austroasiatic language spoken in India’s Nicobar Islands.
  • B. Bonville
    Bonville is a small rural locality in New South Wales, Australia, known for its scenic countryside and proximity to the coastal city of Coffs Harbour.
  • C. Mareuil
    Mareuil is a French surname most notably associated with Simone Mareuil, an actress known for her role in the surrealist film "Un Chien Andalou."
  • D. Dolancourt
    Dolancourt is a small commune in northeastern France’s Grand Est region, known for hosting the Nigloland amusement park.
  • E. Châteaurenault
    Châteaurenault was a notable 17th-century French naval officer and admiral who played a key role in several major maritime conflicts of his time.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: de Tosny
Triple: [Adeliza de Tosny, familyName, de Tosny]
Generated description
De Tosny is a Norman noble family name associated with several medieval aristocratic lineages in England and Normandy.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: de Tosny
Target entity description: De Tosny is a Norman noble family name associated with several medieval aristocratic lineages in England and Normandy.
  • A. Nancoury
    Nancoury is an alternative name for the Nancowry language, an Austroasiatic language spoken in India’s Nicobar Islands.
  • B. Bonville
    Bonville is a small rural locality in New South Wales, Australia, known for its scenic countryside and proximity to the coastal city of Coffs Harbour.
  • C. Mareuil
    Mareuil is a French surname most notably associated with Simone Mareuil, an actress known for her role in the surrealist film "Un Chien Andalou."
  • D. Dolancourt
    Dolancourt is a small commune in northeastern France’s Grand Est region, known for hosting the Nigloland amusement park.
  • E. Châteaurenault
    Châteaurenault was a notable 17th-century French naval officer and admiral who played a key role in several major maritime conflicts of his time.
  • F. None of above. chosen

Provenance (5 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_69e0b4cd25088190b48ca9700cd24efc completed April 16, 2026, 10:07 a.m.
NER Named-entity recognition batch_69e6c2d27a4881908b34679385d8b94b completed April 21, 2026, 12:20 a.m.
NED1 Entity disambiguation (via context triple) batch_6a08f8cb61388190922a898ee4c44d2e completed May 16, 2026, 11:07 p.m.
NEDg Description generation batch_6a08f9deb9248190af178b5c28728e00 completed May 16, 2026, 11:12 p.m.
NED2 Entity disambiguation (via description) batch_6a08fa80202c8190929f8f1b47d6fae4 completed May 16, 2026, 11:15 p.m.
Created at: April 16, 2026, 12:40 p.m.