Triple
T3378069
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sacha Dhawan |
E71113
|
entity |
| Predicate | appearedIn |
P795
|
FINISHED |
| Object | Line of Duty |
E348021
|
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: Line of Duty | Statement: [Sacha Dhawan, appearedIn, Line of Duty]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Line of Duty Context triple: [Sacha Dhawan, appearedIn, Line of Duty]
-
A.
Line of Duty
chosen
Line of Duty is a British crime drama television series that follows an anti-corruption police unit investigating complex and morally ambiguous cases within the force.
-
B.
MI-5
MI-5 is a British spy thriller film (also known as "Spooks: The Greater Good") based on the TV series "Spooks," featuring David Oyelowo in a prominent role.
-
C.
Spooks
Spooks is a British television spy drama series centered on the high-stakes operations of MI5 officers.
-
D.
Silent Witness
Silent Witness is a long-running British crime drama television series that follows forensic pathologists as they investigate complex and often disturbing deaths.
-
E.
Peaky Blinders
Peaky Blinders is a British period crime drama television series following the ruthless Shelby crime family in post-World War I Birmingham.
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2eacb5c81908071a1dacc9a897a |
completed | March 8, 2026, 5:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b34bc17dd881908fc5fb0d4a23f40f |
completed | March 12, 2026, 11:26 p.m. |
Created at: March 8, 2026, 3:13 p.m.