Triple

T25570728
Position Surface form Disambiguated ID Type / Status
Subject Madame de Sévigné E640965 entity
Predicate primaryCorrespondenceRecipient P92617 FINISHED
Object her daughter Françoise-Marguerite
Françoise-Marguerite was the daughter of the famed French letter-writer Madame de Sévigné and the principal recipient of her celebrated correspondence.
 E1687423 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: her daughter Françoise-Marguerite | Statement: [Madame de Sévigné, primaryCorrespondenceRecipient, her daughter Françoise-Marguerite]
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: her daughter Françoise-Marguerite
Triple: [Madame de Sévigné, primaryCorrespondenceRecipient, her daughter Françoise-Marguerite]
Generated description
Françoise-Marguerite was the daughter of the famed French letter-writer Madame de Sévigné and the principal recipient of her celebrated correspondence.
PD Predicate disambiguation gpt-5-mini-2025-08-07 
Target predicate: primaryCorrespondenceRecipient
Context triple: [Madame de Sévigné, primaryCorrespondenceRecipient, her daughter Françoise-Marguerite]
  • A. primaryRecipient
    Indicates the entity that is the main or principal receiver of something, such as a message, resource, or benefit, in a given context.
  • B. principalInterlocutor
    Indicates that one entity serves as the main or primary conversational partner or speaker in an interaction with another entity.
  • C. mainRecipientPosition
    Indicates the role or job position held by the primary recipient in a given interaction or transaction.
  • D. addresseeOf chosen
    Indicates that one entity is the intended recipient or target audience of a communication, message, or expression from another entity.
  • E. individualRecipient
    Indicates that a specific individual is the direct recipient or beneficiary of something (such as an item, message, or action).
  • 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_69e75dc281bc819095ec04dc0c3a94d0 completed April 21, 2026, 11:21 a.m.
NER Named-entity recognition batch_69fb563aec448190875410fb1a3ed624 completed May 6, 2026, 2:54 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10b75a7c3c81909b8f8f24917266ce completed May 22, 2026, 8:06 p.m.
NEDg Description generation batch_6a10b82504908190904c1ed84610e0c4 completed May 22, 2026, 8:10 p.m.
NED2 Entity disambiguation (via description) batch_6a10b9606818819094491a74c5922378 completed May 22, 2026, 8:15 p.m.
PD Predicate disambiguation batch_69fb35b9ede881908aaae93a215525df completed May 6, 2026, 12:36 p.m.
Created at: April 21, 2026, 3:57 p.m.