Triple
T19866060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Colditz Story |
E477392
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Ivan Foxwell |
—
|
NE NERFINISHED |
How this triple was built (2 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: Ivan Foxwell | Statement: [The Colditz Story, screenwriter, Ivan Foxwell]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ivan Foxwell Context triple: [The Colditz Story, screenwriter, Ivan Foxwell]
-
A.
Ivan Foxwell
chosen
Ivan Foxwell was a British screenwriter and film producer known for his work on mid-20th-century British cinema, including notable war and drama films.
-
B.
Nick Jowett
Nick Jowett is a professional colleague of Ian Fletcher, known for collaborating with him in a shared work context.
-
C.
Ben Brockman
Ben Brockman is a mischievous and quick-witted middle child in the British sitcom "Outnumbered," known for his imaginative questions and offbeat logic.
-
D.
Eric Jumper
Eric Jumper is an American engineer and researcher best known for his pioneering scientific investigations into the Shroud of Turin as part of the Shroud of Turin Research Project.
-
E.
Michael Grunst
Michael Grunst is a German local politician who serves as the borough mayor of Berlin’s Lichtenberg district.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51e7d948190aedbcd6c30361c39 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6589f9654819080597a4f7c52d64c |
completed | April 20, 2026, 4:47 p.m. |
Created at: April 10, 2026, 1:51 p.m.