Triple

T30848498
Position Surface form Disambiguated ID Type / Status
Subject Nathaniel Parker Willis E785709 entity
Predicate spouse P13 FINISHED
Object Mary Stace
Mary Stace was the wife of 19th-century American author and editor Nathaniel Parker Willis, known primarily through her marriage into his prominent literary and social circle.
 E1939524 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: Mary Stace | Statement: [Nathaniel Parker Willis, spouse, Mary Stace]
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: Mary Stace
Triple: [Nathaniel Parker Willis, spouse, Mary Stace]
Generated description
Mary Stace was the wife of 19th-century American author and editor Nathaniel Parker Willis, known primarily through her marriage into his prominent literary and social circle.

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_69f224b850848190a4af4ccf8ddadcdf completed April 29, 2026, 3:33 p.m.
NER Named-entity recognition batch_69f6917a847481909d9339914f9c89e5 completed May 3, 2026, 12:06 a.m.
NED1 Entity disambiguation (via context triple) batch_6a28e452a05c81909ade6e63aecaf074 completed June 10, 2026, 4:13 a.m.
NEDg Description generation batch_6a28e71c959081908333190484781b57 completed June 10, 2026, 4:25 a.m.
NED2 Entity disambiguation (via description) batch_6a28e74d21e48190b460d64a5ff4c1d9 completed June 10, 2026, 4:25 a.m.
Created at: April 29, 2026, 8:46 p.m.