Triple
T21970957
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John and Mary |
E542585
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object | Ben Kadish |
—
|
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: Ben Kadish | Statement: [John and Mary, producer, Ben Kadish]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ben Kadish Context triple: [John and Mary, producer, Ben Kadish]
-
A.
Ben Kadish
chosen
Ben Kadish was a film producer active in mid-20th-century American cinema, notably involved in the production of the 1961 musical film "Fanny."
-
B.
Kevin Kadish
Kevin Kadish is an American songwriter and producer best known for co-writing and producing Meghan Trainor’s breakout hit "All About That Bass."
-
C.
Ben Dorfman
Ben Dorfman is a fictional character in Woody Allen’s 2016 romantic comedy film "Café Society."
-
D.
Leon Berkowitz
Leon Berkowitz was an American abstract painter associated with the Washington Color School, known for his luminous color fields and atmospheric explorations of light.
-
E.
Marty Adelstein
Marty Adelstein is an American television producer and executive known for developing and producing numerous popular TV series.
- 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_69e0c48070988190909db97667b9a0ac |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f12484b83081908c08e3285e0b14a9 |
completed | April 28, 2026, 9:20 p.m. |
Created at: April 16, 2026, 8:02 p.m.