Triple

T34268526

Position	Surface form	Disambiguated ID	Type / Status
Subject	Baron of Rosny	`E879240`	entity
Predicate	titleHolderFormerReligion	`P111`	FINISHED
Object	Huguenot (Maximilien de Béthune) Huguenot (Maximilien de Béthune) was a prominent French statesman and close advisor to King Henry IV, best known for serving as Superintendent of Finances and later becoming the Duke of Sully.	`E2091581`	NE FINISHED

How this triple was built (3 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: Huguenot (Maximilien de Béthune) | Statement: [Baron of Rosny, titleHolderFormerReligion, Huguenot (Maximilien de Béthune)]

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: Huguenot (Maximilien de Béthune)
Triple: [Baron of Rosny, titleHolderFormerReligion, Huguenot (Maximilien de Béthune)]

Generated description

Huguenot (Maximilien de Béthune) was a prominent French statesman and close advisor to King Henry IV, best known for serving as Superintendent of Finances and later becoming the Duke of Sully.

PD Predicate disambiguation gpt-5-mini-2025-08-07

Target predicate: titleHolderFormerReligion
Context triple: [Baron of Rosny, titleHolderFormerReligion, Huguenot (Maximilien de Béthune)]

A. titleHolderReligion
Indicates the religious affiliation associated with the holder of a particular title.
B. formerReligiousAffiliation chosen
Indicates that an entity previously adhered to a particular religion or religious denomination but no longer does so.
C. titleHolderLaterReligion
Indicates that the person holding a particular title at a later time follows a specified religion.
D. hasFormerReligiousHouse
Indicates that an entity once contained or was associated with a religious house (such as a monastery, convent, or similar institution) that no longer exists or functions in that capacity.
E. creatorReligiousAffiliation
Indicates the religious affiliation or tradition with which a creator is associated.
F. None of above.

Provenance (6 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_69f349b4f5fc819094b441d18e95e5f1`	completed	April 30, 2026, 12:23 p.m.
NER	Named-entity recognition	`batch_69ff2fbae9b48190847eefa1c227d43e`	completed	May 9, 2026, 12:59 p.m.
NED1	Entity disambiguation (via context triple)	`batch_6a36f9bb94508190af32b46bbdb79588`	completed	June 20, 2026, 8:36 p.m.
NEDg	Description generation	`batch_6a36fc20a7b88190b3460b10d41af555`	completed	June 20, 2026, 8:46 p.m.
NED2	Entity disambiguation (via description)	`batch_6a36fc7936148190991713b65957270e`	completed	June 20, 2026, 8:47 p.m.
PD	Predicate disambiguation	`batch_69ff2f2218048190a32224a648182b5d`	completed	May 9, 2026, 12:57 p.m.

Created at: May 1, 2026, 1:56 a.m.