Triple
T671628
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Torchwood |
E12982
|
entity |
| Predicate | stars |
P1956
|
FINISHED |
| Object |
Kai Owen
Kai Owen is a Welsh actor best known for his role as Rhys Williams in the BBC science fiction series Torchwood.
|
E83673
|
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: Kai Owen | Statement: [Torchwood, stars, Kai Owen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kai Owen Context triple: [Torchwood, stars, Kai Owen]
-
A.
Dominic Lewis
Dominic Lewis is a British-born film and television composer known for scoring a variety of Hollywood projects across action, animation, and comedy.
-
B.
Callum McDougall
Callum McDougall is a British film producer known for his work on major feature films, including the World War I epic "1917."
-
C.
Tyler Bates
Tyler Bates is an American composer best known for his dynamic film and television scores, including work on action franchises like John Wick and superhero films such as Guardians of the Galaxy.
-
D.
Andy King
Andy King is one of the sons of the late American television and radio host Larry King.
-
E.
David Miller
David Miller is a Canadian politician and lawyer best known for serving as the 63rd mayor of Toronto from 2003 to 2010, during which he focused on urban environmental initiatives and public transit expansion.
- 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: Kai Owen Triple: [Torchwood, stars, Kai Owen]
Generated description
Kai Owen is a Welsh actor best known for his role as Rhys Williams in the BBC science fiction series Torchwood.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kai Owen Target entity description: Kai Owen is a Welsh actor best known for his role as Rhys Williams in the BBC science fiction series Torchwood.
-
A.
Dominic Lewis
Dominic Lewis is a British-born film and television composer known for scoring a variety of Hollywood projects across action, animation, and comedy.
-
B.
Callum McDougall
Callum McDougall is a British film producer known for his work on major feature films, including the World War I epic "1917."
-
C.
Tyler Bates
Tyler Bates is an American composer best known for his dynamic film and television scores, including work on action franchises like John Wick and superhero films such as Guardians of the Galaxy.
-
D.
Andy King
Andy King is one of the sons of the late American television and radio host Larry King.
-
E.
David Miller
David Miller is a Canadian politician and lawyer best known for serving as the 63rd mayor of Toronto from 2003 to 2010, during which he focused on urban environmental initiatives and public transit expansion.
- 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_69a493355dec819098d4244b2fa34885 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a021b908819086f7cfe65def4728 |
completed | March 1, 2026, 8:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5c39f3e1481908f395cdb19cfd2fc |
completed | March 2, 2026, 5:06 p.m. |
| NEDg | Description generation | batch_69a5c42d4a0481908af4a71b4625c130 |
completed | March 2, 2026, 5:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a5ce16df088190850a3b851558eba8 |
completed | March 2, 2026, 5:51 p.m. |
Created at: March 1, 2026, 7:36 p.m.