Triple

T21993914
Position Surface form Disambiguated ID Type / Status
Subject Smithy E543153 entity
Predicate screenPartner P46690 FINISHED
Object Nessa Jenkins NE NERFINISHED

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: Nessa Jenkins | Statement: [Smithy, screenPartner, Nessa Jenkins]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Nessa Jenkins
Context triple: [Smithy, screenPartner, Nessa Jenkins]
  • A. Nessa Jenkins chosen
    Nessa Jenkins is a deadpan, no-nonsense Welsh character from the British sitcom "Gavin & Stacey," known for her eccentric stories and iconic catchphrases.
  • B. Jennifer Jenkins
    Jennifer Jenkins is known as the wife of musician Tom DeLonge, co-founder and former guitarist of the rock band Blink-182.
  • C. Samantha Jenkins
    Samantha Jenkins is known as the sister of American actor Maxwell Jenkins.
  • D. Tamara Jenkins
    Tamara Jenkins is an American filmmaker and screenwriter best known for her sharp, character-driven independent films such as "Slums of Beverly Hills" and "The Savages."
  • E. Megs Jenkins
    Megs Jenkins was a British character actress known for her warm, often maternal roles in mid-20th-century film, television, and theatre.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e2c814c8190837d072789000486 completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127639bf48190800b3fa3c1527983 completed April 28, 2026, 9:32 p.m.
Created at: April 16, 2026, 8:17 p.m.