Triple
T5317672
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dixon of Dock Green |
E121590
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Andy Crawford
Andy Crawford is a young police constable who serves as one of the main supporting officers in the long-running British television series "Dixon of Dock Green."
|
E511842
|
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: Andy Crawford | Statement: [Dixon of Dock Green, character, Andy Crawford]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Andy Crawford Context triple: [Dixon of Dock Green, character, Andy Crawford]
-
A.
Ian Crafford
Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
-
B.
James Lloyd Crawford
James Lloyd Crawford was the second husband of pioneering African American actress and Oscar winner Hattie McDaniel.
-
C.
Andy Cullen
Andy Cullen is a fictional character from the classic 1950 film noir "The Man Who Cheated Himself."
-
D.
Andrew Rennison
Andrew Rennison is a British public official known for serving as the inaugural Surveillance Camera Commissioner, overseeing the regulation and ethical use of CCTV and related surveillance technologies in the UK.
-
E.
Chris Henderson
Chris Henderson is an American guitarist best known as a longtime member of the rock band 3 Doors Down.
- 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: Andy Crawford Triple: [Dixon of Dock Green, character, Andy Crawford]
Generated description
Andy Crawford is a young police constable who serves as one of the main supporting officers in the long-running British television series "Dixon of Dock Green."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Andy Crawford Target entity description: Andy Crawford is a young police constable who serves as one of the main supporting officers in the long-running British television series "Dixon of Dock Green."
-
A.
Ian Crafford
Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
-
B.
James Lloyd Crawford
James Lloyd Crawford was the second husband of pioneering African American actress and Oscar winner Hattie McDaniel.
-
C.
Andy Cullen
Andy Cullen is a fictional character from the classic 1950 film noir "The Man Who Cheated Himself."
-
D.
Andrew Rennison
Andrew Rennison is a British public official known for serving as the inaugural Surveillance Camera Commissioner, overseeing the regulation and ethical use of CCTV and related surveillance technologies in the UK.
-
E.
Chris Henderson
Chris Henderson is an American guitarist best known as a longtime member of the rock band 3 Doors Down.
- 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_69bd463d956c819088105c3db802c017 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd855269ac8190bb7a9248d04f1823 |
completed | March 20, 2026, 5:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bf188d3a2c8190ad06d1b71ef73780 |
completed | March 21, 2026, 10:15 p.m. |
| NEDg | Description generation | batch_69bf195d26e88190b86c16cd6adc7c5c |
completed | March 21, 2026, 10:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf1a0bbed08190bf21bd99343b90a4 |
completed | March 21, 2026, 10:22 p.m. |
Created at: March 20, 2026, 1:59 p.m.