Triple
T18755311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Killing Fields |
E458632
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | Goldcrest Films |
—
|
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: Goldcrest Films | Statement: [The Killing Fields, productionCompany, Goldcrest Films]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Goldcrest Films Context triple: [The Killing Fields, productionCompany, Goldcrest Films]
-
A.
Goldcrest Films
chosen
Goldcrest Films is a British film production company best known for backing acclaimed films such as the Oscar-winning "Chariots of Fire."
-
B.
Kestrel Films
Kestrel Films is a British film production company best known for producing Ken Loach’s acclaimed 1969 drama "Kes."
-
C.
Celandine Films
Celandine Films is a film production company best known for producing the British comedy film "Monty Python’s The Meaning of Life."
-
D.
Silverwood Films
Silverwood Films is an independent film production company known for backing critically acclaimed dramas such as "Blue Valentine."
-
E.
Goldenlight Films
Goldenlight Films is a film and video production company associated with projects by the musician and filmmaker St. Vincent (Annie Clark).
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e579f084208190a4b3563d47154e69 |
completed | April 20, 2026, 12:57 a.m. |
Created at: April 10, 2026, 11:51 a.m.