Triple
T22102294
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ships with Wings |
E546199
|
entity |
| Predicate | castMember |
P1668
|
FINISHED |
| Object |
Joss Ambler
Joss Ambler was a British character actor known for his supporting roles in numerous films during the 1930s and 1940s.
|
E1521650
|
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: Joss Ambler | Statement: [Ships with Wings, castMember, Joss Ambler]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joss Ambler Context triple: [Ships with Wings, castMember, Joss Ambler]
-
A.
Alan Shallcross
Alan Shallcross was a British television producer best known for his work on acclaimed drama and anthology series for the BBC.
-
B.
Nick Briggs
Nick Briggs is a photographer known for his work on the television series Downton Abbey and related publications.
-
C.
Michael Greenwood
Michael Greenwood is a member of the Greenwood family, known primarily as a son of British politician Hamar Greenwood, 1st Viscount Greenwood.
-
D.
Christopher Bram
Christopher Bram is an American novelist and essayist best known for his psychologically rich fiction, including the novel that inspired the film "Gods and Monsters."
-
E.
Michael Bentine
Michael Bentine was a British comedian, actor, and founding member of The Goon Show, known for his inventive and often surreal humor in radio, television, and film.
- 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: Joss Ambler Triple: [Ships with Wings, castMember, Joss Ambler]
Generated description
Joss Ambler was a British character actor known for his supporting roles in numerous films during the 1930s and 1940s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Joss Ambler Target entity description: Joss Ambler was a British character actor known for his supporting roles in numerous films during the 1930s and 1940s.
-
A.
Alan Shallcross
Alan Shallcross was a British television producer best known for his work on acclaimed drama and anthology series for the BBC.
-
B.
Nick Briggs
Nick Briggs is a photographer known for his work on the television series Downton Abbey and related publications.
-
C.
Michael Greenwood
Michael Greenwood is a member of the Greenwood family, known primarily as a son of British politician Hamar Greenwood, 1st Viscount Greenwood.
-
D.
Christopher Bram
Christopher Bram is an American novelist and essayist best known for his psychologically rich fiction, including the novel that inspired the film "Gods and Monsters."
-
E.
Michael Bentine
Michael Bentine was a British comedian, actor, and founding member of The Goon Show, known for his inventive and often surreal humor in radio, television, and film.
- 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_69e11e378dc08190896d6a51597afd5a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f129163b908190b63ace06016f4db8 |
completed | April 28, 2026, 9:39 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a96ed8b508190b92bcf06d2f69b25 |
completed | May 18, 2026, 4:34 a.m. |
| NEDg | Description generation | batch_6a0a97a03abc8190a0158fe2ad6c14d7 |
completed | May 18, 2026, 4:37 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a981c96648190b295c1667f1c3648 |
completed | May 18, 2026, 4:39 a.m. |
Created at: April 16, 2026, 8:30 p.m.