Triple
T5600903
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Billy Budd |
E147115
|
entity |
| Predicate | operaLibrettist |
P59320
|
FINISHED |
| Object |
Eric Crozier
Eric Crozier was a British theatrical director, producer, and writer best known for his close collaboration with composer Benjamin Britten on several operas.
|
E559834
|
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: Eric Crozier | Statement: [Billy Budd, operaLibrettist, Eric Crozier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Eric Crozier Context triple: [Billy Budd, operaLibrettist, Eric Crozier]
-
A.
Stan Cullimore
Stan Cullimore is an English guitarist and songwriter best known as a founding member of the 1980s indie pop band The Housemartins.
-
B.
Ian Crafford
Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
-
C.
John Brett
John Brett was a 19th-century British painter associated with the Pre-Raphaelite movement, renowned for his highly detailed landscapes and maritime scenes.
-
D.
Stephen Pycroft
Stephen Pycroft is a British businessman best known as the founder of the construction and consultancy company Mace Group.
-
E.
Greg Shephard
Greg Shephard is a television producer best known for his executive production work on the true-crime drama series "The Act."
- 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: Eric Crozier Triple: [Billy Budd, operaLibrettist, Eric Crozier]
Generated description
Eric Crozier was a British theatrical director, producer, and writer best known for his close collaboration with composer Benjamin Britten on several operas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Eric Crozier Target entity description: Eric Crozier was a British theatrical director, producer, and writer best known for his close collaboration with composer Benjamin Britten on several operas.
-
A.
Stan Cullimore
Stan Cullimore is an English guitarist and songwriter best known as a founding member of the 1980s indie pop band The Housemartins.
-
B.
Ian Crafford
Ian Crafford is a film editor best known for his work on the James Bond movie "Never Say Never Again."
-
C.
John Brett
John Brett was a 19th-century British painter associated with the Pre-Raphaelite movement, renowned for his highly detailed landscapes and maritime scenes.
-
D.
Stephen Pycroft
Stephen Pycroft is a British businessman best known as the founder of the construction and consultancy company Mace Group.
-
E.
Greg Shephard
Greg Shephard is a television producer best known for his executive production work on the true-crime drama series "The Act."
- 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_69c009043d648190a7af89698ccf1e3e |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c021d8d600819097df4e265e262d90 |
completed | March 22, 2026, 5:07 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c0e3158cfc8190b2f1a0eb40e8a440 |
completed | March 23, 2026, 6:52 a.m. |
| NEDg | Description generation | batch_69c0f788922c81908aef1b9e93cca18c |
completed | March 23, 2026, 8:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c0f85fb6f88190bef34865d649fbff |
completed | March 23, 2026, 8:22 a.m. |
Created at: March 22, 2026, 3:38 p.m.