Triple

T14449503
Position Surface form Disambiguated ID Type / Status
Subject Toclafane E358293 entity
Predicate antagonistOf P18963 FINISHED
Object Captain Jack Harkness E88094 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: Captain Jack Harkness | Statement: [Toclafane, antagonistOf, Captain Jack Harkness]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Captain Jack Harkness
Context triple: [Toclafane, antagonistOf, Captain Jack Harkness]
  • A. Captain Jack Harkness chosen
    Captain Jack Harkness is a charismatic, time-traveling former Time Agent and immortal leader of the Torchwood Institute in the Doctor Who universe.
  • B. Alistair Smythe
    Alistair Smythe is a Marvel Comics supervillain and scientific genius best known as an enemy of Spider-Man and the creator of the deadly Spider-Slayer robots.
  • C. John Lethbridge
    John Lethbridge was the father of Claire Clairmont, the stepsister of Mary Shelley and a member of the literary circle surrounding Percy Bysshe Shelley and Lord Byron.
  • D. Dominic Rathbone
    Dominic Rathbone is a historian and papyrologist specializing in the social and economic history of the Graeco-Roman world, particularly Roman Egypt.
  • E. Marc Warren
    Marc Warren is an English actor known for his versatile roles in British television dramas and films, including prominent parts in series like "Hustle" and "Mad Dogs."
  • 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_69d82794dfa081909b9134ad2e32244b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de916139888190be219678e29a2a3a completed April 14, 2026, 7:11 p.m.
NED1 Entity disambiguation (via context triple) batch_69fde163c3488190aac5a8bd769d5564 completed May 8, 2026, 1:13 p.m.
Created at: April 10, 2026, 1:19 a.m.