Triple

T37258132
Position Surface form Disambiguated ID Type / Status
Subject Anne Hilarion de Costentin de Tourville E924187 entity
Predicate hasFamilyName P18 FINISHED
Object de Costentin
de Costentin is a French noble family name historically associated with figures such as the naval commander Anne Hilarion de Costentin de Tourville.
 E2218829 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: de Costentin | Statement: [Anne Hilarion de Costentin de Tourville, hasFamilyName, de Costentin]
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 Costentin
Triple: [Anne Hilarion de Costentin de Tourville, hasFamilyName, de Costentin]
Generated description
de Costentin is a French noble family name historically associated with figures such as the naval commander Anne Hilarion de Costentin de Tourville.

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_69f76eabd6c481909d414a80a1345c98 completed May 3, 2026, 3:50 p.m.
NER Named-entity recognition batch_69fb372da9248190bab2b04711f839f4 completed May 6, 2026, 12:42 p.m.
NED1 Entity disambiguation (via context triple) batch_6a4043d5e52881908b0389df16e02fd4 completed June 27, 2026, 9:42 p.m.
NEDg Description generation batch_6a404461ff1c8190ae3ed2dbedc8dc48 completed June 27, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_6a40457ebde88190b43dc9291ec1b2de completed June 27, 2026, 9:49 p.m.
Created at: May 3, 2026, 4:15 p.m.