Triple
T17436095
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ikiru |
E424004
|
entity |
| Predicate | hasTitleInLanguage |
P15390
|
FINISHED |
| Object | Ikiru (Japanese) |
—
|
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: Ikiru (Japanese) | Statement: [Ikiru, hasTitleInLanguage, Ikiru (Japanese)]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ikiru (Japanese) Context triple: [Ikiru, hasTitleInLanguage, Ikiru (Japanese)]
-
A.
Ikiru
chosen
Ikiru is a 1952 Japanese drama film directed by Akira Kurosawa that follows a terminally ill bureaucrat’s search for meaning in his final days.
-
B.
Ikiru Films
Ikiru Films is a Spanish film production company known for backing acclaimed international and auteur-driven cinema.
-
C.
Onibaba
Onibaba is a 1964 Japanese horror film by Kaneto Shindō, renowned for its stark black-and-white imagery and allegorical tale of survival, violence, and desire set in medieval rural Japan.
-
D.
Canegata
Canegata is the original surname of the influential African-American actor and civil rights activist Canada Lee.
-
E.
Private: The Tokyo Story
Private: The Tokyo Story is an adult film title from the "Private" series, known for its explicit erotic content set against a Tokyo backdrop.
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4490426008190b474ed76aca5d6f3 |
completed | April 19, 2026, 3:16 a.m. |
Created at: April 10, 2026, 5:46 a.m.