Triple
T11740886
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Collector |
E279149
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | John Kohn |
E948806
|
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: John Kohn | Statement: [The Collector, screenwriter, John Kohn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Kohn Context triple: [The Collector, screenwriter, John Kohn]
-
A.
John Kohn
chosen
John Kohn was a British film producer known for his work on notable mid-20th-century films, including the psychological thriller "The Collector."
-
B.
John Eisendrath
John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
-
C.
David Kahne
David Kahne is an American record producer and engineer known for his work with major artists across rock and pop, including Paul McCartney.
-
D.
Thomas J. Biersteker
Thomas J. Biersteker is an American political scientist and international relations scholar known for his work on global governance, sanctions, and international security.
-
E.
Christopher Keyser
Christopher Keyser is an American television writer and producer best known for co-creating the drama series "Party of Five" and working on numerous other network and streaming shows.
- 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_69d6aaffec6881908bead509e8621742 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a4f025f88190a39280806c9d7c33 |
completed | April 10, 2026, 7:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f16679c0ec81909fe80d75dd582db1 |
completed | April 29, 2026, 2:01 a.m. |
Created at: April 8, 2026, 9:41 p.m.