Triple
T13354001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jobs |
E318140
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Mark Hulme |
E80734
|
NE FINISHED |
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: Mark Hulme | Statement: [Jobs, producer, Mark Hulme]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Hulme Context triple: [Jobs, producer, Mark Hulme]
-
A.
Mark Hulme
chosen
Mark Hulme is a film producer best known for producing the 2013 biographical drama "Jobs" about Apple co-founder Steve Jobs.
-
B.
Bruce Hough
Bruce Hough is an American businessman and political figure best known as the father of professional dancer and actress Julianne Hough.
-
C.
Timothy Mertens
Timothy Mertens is a film editor best known for his work on animated features such as "Horton Hears a Who!".
-
D.
Ian Hallard
Ian Hallard is a British actor and writer known for his work in television, theatre, and radio, as well as for his collaborations with his husband, writer-actor Mark Gatiss.
-
E.
Kent Hull
Kent Hull was an American football center best known for anchoring the Buffalo Bills’ offensive line during their early 1990s Super Bowl runs.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d806b5a3c08190b42c267fb092f98a |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d99e8d520881908aa23c7102b72b72 |
completed | April 11, 2026, 1:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f71f49e5548190b14d09daea628e6b |
completed | May 3, 2026, 10:11 a.m. |
Created at: April 9, 2026, 9:32 p.m.