Triple

T19119458
Position Surface form Disambiguated ID Type / Status
Subject Torchwood: Children of Earth E468001 entity
Predicate featuresCharacter P626 FINISHED
Object Lois Habiba 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: Lois Habiba | Statement: [Torchwood: Children of Earth, featuresCharacter, Lois Habiba]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Lois Habiba
Context triple: [Torchwood: Children of Earth, featuresCharacter, Lois Habiba]
  • A. Lois Habiba chosen
    Lois Habiba is a fictional civil servant and key supporting character in the Torchwood: Children of Earth television storyline.
  • B. Lois Wilson
    Lois Wilson was an American actress prominent during the silent and early sound film eras, known for her versatile performances in numerous Hollywood productions.
  • C. Lois Meridan
    Lois Meridan is known primarily as the wife of longtime American radio and television talk-show host Joe Franklin.
  • D. Lois Laurel
    Lois Laurel is a character from the 1931 Marx Brothers comedy film "Monkey Business," appearing in the film’s zany, fast-paced storyline.
  • E. Lois Welch
    Lois Welch is an American academic and literary scholar best known for her work preserving and promoting the legacy of her late husband, Native American author James Welch.
  • 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_69d8dd06a26481908039e2a1bae8c597 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e3c810808190a88d5c7859e7c650 completed April 20, 2026, 8:28 a.m.
Created at: April 10, 2026, 12:05 p.m.