Triple

T9512039
Position Surface form Disambiguated ID Type / Status
Subject Estelle Taylor E229420 entity
Predicate marriagePartner P13 FINISHED
Object Paul Small E805586 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: Paul Small | Statement: [Estelle Taylor, marriagePartner, Paul Small]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul Small
Context triple: [Estelle Taylor, marriagePartner, Paul Small]
  • A. Paul Small chosen
    Paul Small was the husband of American film actress Estelle Taylor, known primarily in relation to her personal life.
  • B. Michael Small
    Michael Small was an American film composer best known for his suspenseful and atmospheric scores for 1970s and 1980s thrillers.
  • C. Paul Millspaugh
    Paul Millspaugh is a film editor known for his work on the romantic comedy "Two Can Play That Game."
  • D. Paul Elliott
    Paul Elliott is a cinematographer best known for his work on the 1997 film "Soul Food."
  • E. Paul Qualley
    Paul Qualley is a former American model and rancher best known as the ex-husband of actress Andie MacDowell and the father of actress Margaret Qualley.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69ca84777560819084cddd999badc1aa completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd98699b788190b1a475e1b1883584 completed April 1, 2026, 10:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1526d30a481909944110fd6ebd1dd completed April 4, 2026, 6:03 p.m.
Created at: March 30, 2026, 7:58 p.m.