Triple
T11236213
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Clouds of Sils Maria |
E265946
|
entity |
| Predicate | productionCompany |
P490
|
FINISHED |
| Object | CG Cinéma |
E873124
|
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: CG Cinéma | Statement: [Clouds of Sils Maria, productionCompany, CG Cinéma]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: CG Cinéma Context triple: [Clouds of Sils Maria, productionCompany, CG Cinéma]
-
A.
CG Cinéma
chosen
CG Cinéma is a French film production company known for backing auteur-driven and art-house cinema.
-
B.
CinéCinéma
CinéCinéma is a French television network and film production entity known for supporting and broadcasting a wide range of French and international cinema.
-
C.
CINE
CINE is the London Stock Exchange ticker symbol for Cineworld Group, one of the world’s largest cinema chains.
-
D.
Gaumont
Gaumont is a historic French film and television production company, recognized as one of the oldest continuously operating studios in the world.
-
E.
CINAR
CINAR is the designated radio callsign used by the airline AJet for air traffic control and communication purposes.
- 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_69d6aac656d48190b275efaa7d6074ee |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e904cf888190826fc964f76b5cb2 |
completed | April 9, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e4ad6308f8819085652d6c529ac821 |
completed | April 19, 2026, 10:24 a.m. |
Created at: April 8, 2026, 9:30 p.m.