Triple
T23233154
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Duke of Earl |
E581215
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Bill Sheppard
Bill Sheppard was a music producer best known for his work on the classic early-1960s doo-wop hit "Duke of Earl."
|
E1576251
|
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: Bill Sheppard | Statement: [Duke of Earl, producer, Bill Sheppard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bill Sheppard Context triple: [Duke of Earl, producer, Bill Sheppard]
-
A.
Michael Shea
Michael Shea was a prominent theater entrepreneur and impresario whose legacy in the performing arts is commemorated by the naming of Shea’s Performing Arts Center.
-
B.
Michael Shea
Michael Shea is a fictional character from the long-running American soap opera "As the World Turns," known primarily for his marriage to Lisa Miller Hughes.
-
C.
Michael Robinson
Michael Robinson is a music producer known for his work on the track "The Sea."
-
D.
Jeff Markham
Jeff Markham is the true identity of Jeff Bailey, the enigmatic private detective and antihero in the classic film noir "Out of the Past."
-
E.
Simon Dermott
Simon Dermott is the charming, clever art expert and thief portrayed by Peter O’Toole in the 1966 heist comedy film "How to Steal a Million."
- 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: Bill Sheppard Triple: [Duke of Earl, producer, Bill Sheppard]
Generated description
Bill Sheppard was a music producer best known for his work on the classic early-1960s doo-wop hit "Duke of Earl."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bill Sheppard Target entity description: Bill Sheppard was a music producer best known for his work on the classic early-1960s doo-wop hit "Duke of Earl."
-
A.
Michael Shea
Michael Shea was a prominent theater entrepreneur and impresario whose legacy in the performing arts is commemorated by the naming of Shea’s Performing Arts Center.
-
B.
Michael Shea
Michael Shea is a fictional character from the long-running American soap opera "As the World Turns," known primarily for his marriage to Lisa Miller Hughes.
-
C.
Michael Robinson
Michael Robinson is a music producer known for his work on the track "The Sea."
-
D.
Jeff Markham
Jeff Markham is the true identity of Jeff Bailey, the enigmatic private detective and antihero in the classic film noir "Out of the Past."
-
E.
Simon Dermott
Simon Dermott is the charming, clever art expert and thief portrayed by Peter O’Toole in the 1966 heist comedy film "How to Steal a Million."
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f192e70b2c8190abede6e3cd9344f7 |
completed | April 29, 2026, 5:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c3f59de808190afb414450ac32d0d |
completed | May 19, 2026, 10:45 a.m. |
| NEDg | Description generation | batch_6a0c4008c4a881908ad49e733b549036 |
completed | May 19, 2026, 10:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c40bece448190bb9fd1a3058a1f06 |
completed | May 19, 2026, 10:51 a.m. |
Created at: April 17, 2026, 4:09 p.m.