Triple
T5317676
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dixon of Dock Green |
E121590
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Peter Byrne
Peter Byrne was a British actor best known for his long-running role as Andy Crawford in the classic television police series "Dixon of Dock Green."
|
E522629
|
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: Peter Byrne | Statement: [Dixon of Dock Green, starring, Peter Byrne]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Peter Byrne Context triple: [Dixon of Dock Green, starring, Peter Byrne]
-
A.
William Matthew Byrne Jr.
William Matthew Byrne Jr. was a United States federal judge best known for presiding over the Pentagon Papers case involving Daniel Ellsberg.
-
B.
Michael O’Rourke
Michael O’Rourke is an Irish media entrepreneur best known as a co-founder of the international sports television network Setanta Sports.
-
C.
Michael Byrne
Michael Byrne is a British character actor known for his numerous film and television roles, often portraying military officers or authority figures.
-
D.
Paul Guilfoyle
Paul Guilfoyle is an American actor best known for playing Captain Jim Brass on the long-running television series CSI: Crime Scene Investigation.
-
E.
John Killoran
John Killoran is an actor known for his role in the National Theatre’s acclaimed stage production of "Frankenstein."
- 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: Peter Byrne Triple: [Dixon of Dock Green, starring, Peter Byrne]
Generated description
Peter Byrne was a British actor best known for his long-running role as Andy Crawford in the classic television police series "Dixon of Dock Green."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Peter Byrne Target entity description: Peter Byrne was a British actor best known for his long-running role as Andy Crawford in the classic television police series "Dixon of Dock Green."
-
A.
William Matthew Byrne Jr.
William Matthew Byrne Jr. was a United States federal judge best known for presiding over the Pentagon Papers case involving Daniel Ellsberg.
-
B.
Michael O’Rourke
Michael O’Rourke is an Irish media entrepreneur best known as a co-founder of the international sports television network Setanta Sports.
-
C.
Michael Byrne
Michael Byrne is a British character actor known for his numerous film and television roles, often portraying military officers or authority figures.
-
D.
Paul Guilfoyle
Paul Guilfoyle is an American actor best known for playing Captain Jim Brass on the long-running television series CSI: Crime Scene Investigation.
-
E.
John Killoran
John Killoran is an actor known for his role in the National Theatre’s acclaimed stage production of "Frankenstein."
- 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_69bf4871c22c8190986f12c2783f315a |
completed | March 22, 2026, 1:40 a.m. |
| NEDg | Description generation | batch_69bf49d0ec4881908e835642e2e20cc9 |
completed | March 22, 2026, 1:45 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69bf4a2c4748819080df9bb468fd9198 |
completed | March 22, 2026, 1:47 a.m. |
Created at: March 20, 2026, 1:59 p.m.