Triple
T15035995
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tegan Jovanka |
E378477
|
entity |
| Predicate | associatedWith |
P37
|
FINISHED |
| Object | Vislor Turlough |
E1132696
|
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: Vislor Turlough | Statement: [Tegan Jovanka, associatedWith, Vislor Turlough]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vislor Turlough Context triple: [Tegan Jovanka, associatedWith, Vislor Turlough]
-
A.
Vislor Turlough
chosen
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.
-
B.
Nardole
Nardole is a comedic yet resourceful companion of the Twelfth Doctor in the Doctor Who television series.
-
C.
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."
-
D.
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.
-
E.
Roland Caulder
Roland Caulder is an actor known for his role in the film "The Iron Mask."
- 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_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_69feae0be8bc81909e1f9ed31bfd76fb |
completed | May 9, 2026, 3:46 a.m. |
Created at: April 10, 2026, 2:59 a.m.