Triple
T19915032
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Watership Down (1978 film) |
E478642
|
entity |
| Predicate | cinematography |
P1953
|
FINISHED |
| Object |
Tony Guy
Tony Guy is a cinematographer best known for his work on the 1978 animated film adaptation of "Watership Down."
|
E1401204
|
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: Tony Guy | Statement: [Watership Down (1978 film), cinematography, Tony Guy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Guy Context triple: [Watership Down (1978 film), cinematography, Tony Guy]
-
A.
Peter Cosgrove
Peter Cosgrove is an Australian retired senior Army officer who served as the 26th Governor-General of Australia.
-
B.
Mark Cullen
Mark Cullen is an American screenwriter and producer best known for co-writing the action-comedy film "Cop Out" and creating several television series.
-
C.
Scott Barrett
Scott Barrett is a New Zealand rugby union lock who plays for the Crusaders and the All Blacks.
-
D.
Scott Barrett
Scott Barrett is the child of Kevin Barrett, likely known in relation to his father.
-
E.
Stephen McKeon
Stephen McKeon is an Irish composer best known for his work on film and television scores, including the soundtrack for the series "Queen and Country."
- 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: Tony Guy Triple: [Watership Down (1978 film), cinematography, Tony Guy]
Generated description
Tony Guy is a cinematographer best known for his work on the 1978 animated film adaptation of "Watership Down."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tony Guy Target entity description: Tony Guy is a cinematographer best known for his work on the 1978 animated film adaptation of "Watership Down."
-
A.
Peter Cosgrove
Peter Cosgrove is an Australian retired senior Army officer who served as the 26th Governor-General of Australia.
-
B.
Mark Cullen
Mark Cullen is an American screenwriter and producer best known for co-writing the action-comedy film "Cop Out" and creating several television series.
-
C.
Scott Barrett
Scott Barrett is a New Zealand rugby union lock who plays for the Crusaders and the All Blacks.
-
D.
Scott Barrett
Scott Barrett is the child of Kevin Barrett, likely known in relation to his father.
-
E.
Stephen McKeon
Stephen McKeon is an Irish composer best known for his work on film and television scores, including the soundtrack for the series "Queen and Country."
- 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_69d8e521855c8190b41871700afc8d6a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6599394f081909246006c2e83bacc |
completed | April 20, 2026, 4:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07ea4fc6bc81909573e05b842ec0ab |
completed | May 16, 2026, 3:53 a.m. |
| NEDg | Description generation | batch_6a07eef4995c81909b45b0e84de19c34 |
completed | May 16, 2026, 4:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07ef716f68819093a9a6356080e39e |
completed | May 16, 2026, 4:15 a.m. |
Created at: April 10, 2026, 1:53 p.m.