Triple

T18839803
Position Surface form Disambiguated ID Type / Status
Subject Henrietta "Hetty" Lange E460761 entity
Predicate supervises P258 FINISHED
Object Kensi Blye 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: Kensi Blye | Statement: [Henrietta "Hetty" Lange, supervises, Kensi Blye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kensi Blye
Context triple: [Henrietta "Hetty" Lange, supervises, Kensi Blye]
  • A. Kensi Blye chosen
    Kensi Blye is a highly skilled and resourceful NCIS Special Agent and former Marine who serves as one of the central protagonists on the television series NCIS: Los Angeles.
  • B. Calleigh Duquesne
    Calleigh Duquesne is a ballistics expert and crime scene investigator on the television series CSI: Miami, known for her Southern charm, professionalism, and forensic expertise.
  • C. March West
    March West is an electoral ward within the town of March in Cambridgeshire, England, represented on the local council.
  • D. Samantha Hobbs
    Samantha Hobbs is the young daughter of DSS agent Luke Hobbs in the Fast & Furious film franchise.
  • E. Claire Temple
    Claire Temple is a compassionate and resourceful nurse in the Marvel universe who frequently aids street-level heroes like Daredevil and Luke Cage, often serving as a crucial moral and medical support.
  • 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_69d8dcfa11e4819090ab1ef5bdcd2b2e completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5b8e8f57081909edbbcaf56189816 completed April 20, 2026, 5:26 a.m.
Created at: April 10, 2026, 11:56 a.m.