Triple

T15035815
Position Surface form Disambiguated ID Type / Status
Subject Fifth Doctor E378473 entity
Predicate travelsWith P881 FINISHED
Object Vislor Turlough
Vislor Turlough is a morally conflicted alien companion in Doctor Who who initially plots against the Fifth Doctor before ultimately reforming and aiding him on his travels.
E1132696 NE FINISHED

How this triple was built (4 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: Vislor Turlough | Statement: [Fifth Doctor, travelsWith, Vislor Turlough]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Vislor Turlough
Context triple: [Fifth Doctor, travelsWith, Vislor Turlough]
  • A. Nardole
    Nardole is a comedic yet resourceful companion of the Twelfth Doctor in the Doctor Who television series.
  • B. Ronan Barrow
    Ronan Barrow is a performer who appeared as a cast member on the comedic courtroom-style television series "Lewis Black's Root of All Evil."
  • C. Geoffrey Keen
    Geoffrey Keen was a British character actor best known for his recurring role as the Minister of Defence in the James Bond film series.
  • D. Roland Caulder
    Roland Caulder is an actor known for his role in the film "The Iron Mask."
  • E. Lankester Merrin
    Lankester Merrin is a fictional Catholic priest and exorcist best known as the central character in the Exorcist film series, particularly for confronting demonic possession.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Vislor Turlough
Triple: [Fifth Doctor, travelsWith, Vislor Turlough]
Generated description
Vislor Turlough is a morally conflicted alien companion in Doctor Who who initially plots against the Fifth Doctor before ultimately reforming and aiding him on his travels.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Vislor Turlough
Target entity description: Vislor Turlough is a morally conflicted alien companion in Doctor Who who initially plots against the Fifth Doctor before ultimately reforming and aiding him on his travels.
  • A. Nardole
    Nardole is a comedic yet resourceful companion of the Twelfth Doctor in the Doctor Who television series.
  • B. Ronan Barrow
    Ronan Barrow is a performer who appeared as a cast member on the comedic courtroom-style television series "Lewis Black's Root of All Evil."
  • C. Geoffrey Keen
    Geoffrey Keen was a British character actor best known for his recurring role as the Minister of Defence in the James Bond film series.
  • D. Roland Caulder
    Roland Caulder is an actor known for his role in the film "The Iron Mask."
  • E. Lankester Merrin
    Lankester Merrin is a fictional Catholic priest and exorcist best known as the central character in the Exorcist film series, particularly for confronting demonic possession.
  • F. None of above. chosen

Provenance (5 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_69d85cd46b2c819090d054c27787f677 completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69ded82b29948190acda49cbec3f927a completed April 15, 2026, 12:13 a.m.
NED1 Entity disambiguation (via context triple) batch_69fe9ddfc13481909333690016650410 completed May 9, 2026, 2:37 a.m.
NEDg Description generation batch_69fe9e7e12488190972b383d66a2651e completed May 9, 2026, 2:39 a.m.
NED2 Entity disambiguation (via description) batch_69fe9f0dd1ac8190a802e9b388b9c770 completed May 9, 2026, 2:42 a.m.
Created at: April 10, 2026, 2:59 a.m.