Triple
T11299886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | If.... |
E267554
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
John Howlett
John Howlett is a British writer best known for his work as a screenwriter and novelist, including co-writing the influential 1968 film "If....".
|
E917887
|
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: John Howlett | Statement: [If...., screenwriter, John Howlett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Howlett Context triple: [If...., screenwriter, John Howlett]
-
A.
Jeffrey Howlett
Jeffrey Howlett was an Australian architect best known for his influential modernist designs, particularly major public buildings in Perth.
-
B.
Ian Craig Marsh
Ian Craig Marsh is a British electronic musician best known as a founding member of pioneering synth-pop bands The Human League and Heaven 17.
-
C.
Jeffrey Stott
Jeffrey Stott is a film producer best known for his work on the political comedy film "The American President."
-
D.
Geoffrey Smith
Geoffrey Smith is an Australian Anglican archbishop who serves as the national leader (Primate) of the Anglican Church of Australia.
-
E.
Nicholas Campbell
Nicholas Campbell is a Canadian actor best known for his work in film and television, including his lead role in the crime drama series "Da Vinci's Inquest."
- 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: John Howlett Triple: [If...., screenwriter, John Howlett]
Generated description
John Howlett is a British writer best known for his work as a screenwriter and novelist, including co-writing the influential 1968 film "If....".
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Howlett Target entity description: John Howlett is a British writer best known for his work as a screenwriter and novelist, including co-writing the influential 1968 film "If....".
-
A.
Jeffrey Howlett
Jeffrey Howlett was an Australian architect best known for his influential modernist designs, particularly major public buildings in Perth.
-
B.
Ian Craig Marsh
Ian Craig Marsh is a British electronic musician best known as a founding member of pioneering synth-pop bands The Human League and Heaven 17.
-
C.
Jeffrey Stott
Jeffrey Stott is a film producer best known for his work on the political comedy film "The American President."
-
D.
Geoffrey Smith
Geoffrey Smith is an Australian Anglican archbishop who serves as the national leader (Primate) of the Anglican Church of Australia.
-
E.
Nicholas Campbell
Nicholas Campbell is a Canadian actor best known for his work in film and television, including his lead role in the crime drama series "Da Vinci's Inquest."
- 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_69d6aac993a08190a6f36445ebaf9a43 |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e9a4aad4819097384e1b591be2e3 |
completed | April 9, 2026, 6:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e50a4af56881908cc395b6687d40a9 |
completed | April 19, 2026, 5 p.m. |
| NEDg | Description generation | batch_69e510f9edb4819097e9fa1ce85504ed |
completed | April 19, 2026, 5:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69e516ac8dec81909c9c1eece372189e |
completed | April 19, 2026, 5:53 p.m. |
Created at: April 8, 2026, 9:32 p.m.