Triple
T20652511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | A Woman & a Man |
E507532
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | David Tickle |
—
|
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: David Tickle | Statement: [A Woman & a Man, producer, David Tickle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: David Tickle Context triple: [A Woman & a Man, producer, David Tickle]
-
A.
David Tickle
chosen
David Tickle is a British record producer and audio engineer known for his work with prominent rock and pop artists from the late 20th century.
-
B.
Michael Tiddes
Michael Tiddes is an American film director best known for helming parody and comedy films such as the spoof horror movie "A Haunted House."
-
C.
Simon Tindall
Simon Tindall is a cinematographer known for his work on the British coming-of-age film "Days of the Bagnold Summer."
-
D.
Duncan Gibbins
Duncan Gibbins was a British film and music video director known for his stylish work in the 1980s, including videos for major pop artists.
-
E.
Jim Tyrer
Jim Tyrer was a dominant All-Pro offensive tackle in the American Football League and NFL, best known for anchoring the Kansas City Chiefs’ offensive line during their championship years.
- 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_69e0b4bf58c081908e52a4500e03ff83 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6af22d6bc8190b9d6877aba5704eb |
completed | April 20, 2026, 10:56 p.m. |
Created at: April 16, 2026, 11:43 a.m.