Triple

T16328924
Position Surface form Disambiguated ID Type / Status
Subject Captain Jack Harkness E396496 entity
Predicate worksWith P398 FINISHED
Object Gwen Cooper E87216 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: Gwen Cooper | Statement: [Captain Jack Harkness, worksWith, Gwen Cooper]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Gwen Cooper
Context triple: [Captain Jack Harkness, worksWith, Gwen Cooper]
  • A. Gwen Cooper chosen
    Gwen Cooper is a compassionate yet tough Welsh police officer who becomes a key member of the secret alien-hunting team in the British sci-fi series Torchwood.
  • B. Gwen
    Gwen is the Allied reporting name for the Mitsubishi Ki-21, a Japanese twin-engine bomber used extensively during World War II.
  • C. Gwen
    Gwen is a feminine given name, often used in English-speaking countries and derived from the Welsh name Gwenhwyfar (Guinevere).
  • D. Gwen Hotchkiss
    Gwen Hotchkiss is a character from the soap opera "Passions," known for her long-running romantic rivalry and dramatic entanglements with Theresa Lopez-Fitzgerald over Ethan Crane.
  • E. Moira MacTaggert
    Moira MacTaggert is a human ally of the X-Men, often portrayed as a brilliant geneticist and expert on mutantkind in Marvel’s X-Men universe.
  • 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_69d87f255b788190a400eba031dd85d8 completed April 10, 2026, 4:40 a.m.
NER Named-entity recognition batch_69e2c4ddc5608190b24fe2e871691470 completed April 17, 2026, 11:40 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00261134108190812da262b424a476 completed May 10, 2026, 6:30 a.m.
Created at: April 10, 2026, 5:07 a.m.