Triple
T19453805
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Carmen Cuba |
E486683
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object | Kimi |
—
|
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: Kimi | Statement: [Carmen Cuba, notableWork, Kimi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kimi Context triple: [Carmen Cuba, notableWork, Kimi]
-
A.
Kimi
chosen
Kimi is a 2022 techno-thriller film starring Zoë Kravitz as an agoraphobic tech worker who uncovers evidence of a violent crime through a virtual assistant’s audio data.
-
B.
Kimi Honda
Kimi Honda was the wife of Japanese film director Ishirō Honda, known for her connection to the influential creator of the Godzilla franchise.
-
C.
Kima
Kima is a small settlement located on Car Nicobar Island in the Nicobar district of India’s Andaman and Nicobar Islands.
-
D.
Kitan
Kitan is a family name most notably associated with the character Drenala Kitan.
-
E.
Ukyo
Ukyo is a Japanese given name commonly used for males and borne by various real and fictional characters.
- 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_69d8e8d86d608190bd199a98d0297f27 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e6339407a08190a3e0213bfbb4df3d |
completed | April 20, 2026, 2:09 p.m. |
Created at: April 10, 2026, 1:38 p.m.