Triple
T20524073
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Pumpkin Eater |
E503887
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Alan Webb
Alan Webb was a British character actor known for his distinguished stage and film career in mid-20th-century England.
|
E1435913
|
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: Alan Webb | Statement: [The Pumpkin Eater, starring, Alan Webb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alan Webb Context triple: [The Pumpkin Eater, starring, Alan Webb]
-
A.
Daniel Patterson
Daniel Patterson was the first husband of Mary Baker Eddy, the founder of Christian Science.
-
B.
Alan Davidson
Alan Davidson is a U.S. technology policy expert and government official who has held senior roles shaping national internet, telecommunications, and digital policy.
-
C.
Michael Gunton
Michael Gunton is a British television producer best known for his work on major BBC natural history series such as Planet Earth II and Dynasties.
-
D.
Jeffrey Hatcher
Jeffrey Hatcher is an American playwright and screenwriter known for his work in theater and film, including adaptations and period dramas.
-
E.
Richard Blais
Richard Blais is an American chef, restaurateur, and television personality known for his inventive, modernist cooking and frequent appearances on culinary competition shows.
- 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: Alan Webb Triple: [The Pumpkin Eater, starring, Alan Webb]
Generated description
Alan Webb was a British character actor known for his distinguished stage and film career in mid-20th-century England.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Alan Webb Target entity description: Alan Webb was a British character actor known for his distinguished stage and film career in mid-20th-century England.
-
A.
Daniel Patterson
Daniel Patterson was the first husband of Mary Baker Eddy, the founder of Christian Science.
-
B.
Alan Davidson
Alan Davidson is a U.S. technology policy expert and government official who has held senior roles shaping national internet, telecommunications, and digital policy.
-
C.
Michael Gunton
Michael Gunton is a British television producer best known for his work on major BBC natural history series such as Planet Earth II and Dynasties.
-
D.
Jeffrey Hatcher
Jeffrey Hatcher is an American playwright and screenwriter known for his work in theater and film, including adaptations and period dramas.
-
E.
Richard Blais
Richard Blais is an American chef, restaurateur, and television personality known for his inventive, modernist cooking and frequent appearances on culinary competition shows.
- 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_69e0b4b3a6e08190ae663701f50fab8e |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e69f48691c8190af0ac959e92e10d9 |
completed | April 20, 2026, 9:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a089d43c6588190a4be58521ca67698 |
completed | May 16, 2026, 4:37 p.m. |
| NEDg | Description generation | batch_6a089e00cde081908dca3893f03e3398 |
completed | May 16, 2026, 4:40 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a089e8a05488190b3470f4ffb5927ce |
completed | May 16, 2026, 4:42 p.m. |
Created at: April 16, 2026, 11:36 a.m.