Triple

T25671567
Position Surface form Disambiguated ID Type / Status
Subject Hugh Dudley Auchincloss Jr. E643687 entity
Predicate spouse P13 FINISHED
Object Maya de Chrapovitsky
Maya de Chrapovitsky is a socialite best known as the wife of American stockbroker and lawyer Hugh D. Auchincloss Jr., stepfather of Jacqueline Kennedy Onassis.
E1692023 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: Maya de Chrapovitsky | Statement: [Hugh Dudley Auchincloss Jr., spouse, Maya de Chrapovitsky]
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: Maya de Chrapovitsky
Triple: [Hugh Dudley Auchincloss Jr., spouse, Maya de Chrapovitsky]
Generated description
Maya de Chrapovitsky is a socialite best known as the wife of American stockbroker and lawyer Hugh D. Auchincloss Jr., stepfather of Jacqueline Kennedy Onassis.

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_69e77e7f69808190ad27df1006f6037a completed April 21, 2026, 1:41 p.m.
NER Named-entity recognition batch_69f5fb3389ac819092997022ed2bc2f8 completed May 2, 2026, 1:25 p.m.
NED1 Entity disambiguation (via context triple) batch_6a10c1579cb08190ac220495cf63aa02 completed May 22, 2026, 8:49 p.m.
NEDg Description generation batch_6a10c25f38548190a7487c7cb829bce0 completed May 22, 2026, 8:53 p.m.
NED2 Entity disambiguation (via description) batch_6a10c4dc54f481909f2e06eaa2d15d43 completed May 22, 2026, 9:04 p.m.
Created at: April 21, 2026, 7:28 p.m.