Triple

T24325871
Position Surface form Disambiguated ID Type / Status
Subject Joan de Beauvoir de Havilland E613098 entity
Predicate alsoKnownAs P39 FINISHED
Object Joan St. John
Joan St. John is an alternate name for Joan de Beauvoir de Havilland, better known as the Academy Award–winning British-American actress Joan Fontaine.
 E1641772 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: Joan St. John | Statement: [Joan de Beauvoir de Havilland, alsoKnownAs, Joan St. John]
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: Joan St. John
Triple: [Joan de Beauvoir de Havilland, alsoKnownAs, Joan St. John]
Generated description
Joan St. John is an alternate name for Joan de Beauvoir de Havilland, better known as the Academy Award–winning British-American actress Joan Fontaine.

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_69e2d7db6d5c819091194918157a7c1f completed April 18, 2026, 1:01 a.m.
NER Named-entity recognition batch_69f292ec92488190bea984d762a1ec47 completed April 29, 2026, 11:23 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0ff83a99ac8190b1b0425d6002e150 completed May 22, 2026, 6:31 a.m.
NEDg Description generation batch_6a0ff96d423881908d81db0b6bc78921 completed May 22, 2026, 6:36 a.m.
NED2 Entity disambiguation (via description) batch_6a0ffa8bb5208190b473d834c40e7ef3 completed May 22, 2026, 6:41 a.m.
Created at: April 18, 2026, 1:54 a.m.