Triple

T6381457
Position Surface form Disambiguated ID Type / Status
Subject Allan Houston E143591 entity
Predicate spouse P13 FINISHED
Object Tamara Houston E143591 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: Tamara Houston | Statement: [Allan Houston, spouse, Tamara Houston]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tamara Houston
Context triple: [Allan Houston, spouse, Tamara Houston]
  • A. Tamara Houston chosen
    Tamara Houston is best known as the wife of former NBA All-Star shooting guard Allan Houston.
  • B. Stephanie Austin
    Stephanie Austin is a film producer known for her work on action and thriller movies, including the 1996 film "The Long Kiss Goodnight."
  • C. Sarah Baldwin
    Sarah Baldwin is an actress known for appearing in the romantic comedy film "Something Borrowed."
  • D. Chynna Phillips
    Chynna Phillips is an American singer and actress best known as a member of the pop group Wilson Phillips.
  • E. Julia Houston
    Julia Houston is a central character in the TV series "Smash," portrayed as a talented but personally conflicted Broadway songwriter and lyricist.
  • 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_69c008dac1ec81909cef8157ccd69962 completed March 22, 2026, 3:20 p.m.
NER Named-entity recognition batch_69c0685385948190938b67bff671072b completed March 22, 2026, 10:08 p.m.
NED1 Entity disambiguation (via context triple) batch_69c62db397f48190bc4533ce26b27a55 completed March 27, 2026, 7:11 a.m.
Created at: March 22, 2026, 4:33 p.m.