Triple
T12390839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Knives Out |
E295988
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | MRC |
E125467
|
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: MRC | Statement: [Knives Out, productionCompany, MRC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: MRC Context triple: [Knives Out, productionCompany, MRC]
-
A.
MRC
chosen
MRC is an American independent film and television studio known for producing and financing a wide range of acclaimed movies and TV series.
-
B.
MRC
MRC is a major UK organization that funds and supports medical research to improve human health.
-
C.
MRC
MRC is an intergovernmental organization that coordinates sustainable development and management of the Mekong River basin among its member countries.
-
D.
MCRC
MCRC is the United States Marine Corps Recruiting Command responsible for enlisting and accessing new Marines into the Corps.
-
E.
MRC Data
MRC Data was a music and entertainment data analytics company best known for tracking and reporting music consumption and chart performance before rebranding as Luminate.
- 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_69d6ad9e653c8190b1473c860ee53dae |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d93fd0bcc48190bb1a59a3aaa6bfdf |
completed | April 10, 2026, 6:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63479df38819085c5ca791c460d5e |
completed | May 2, 2026, 5:29 p.m. |
Created at: April 8, 2026, 9:54 p.m.