Triple
T17749016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Red Sorghum |
E443064
|
entity |
| Predicate | marksDirectorialDebut |
P18940
|
FINISHED |
| Object | Zhang Yimou’s feature directorial debut |
—
|
LITERAL 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: Zhang Yimou’s feature directorial debut | Statement: [Red Sorghum, marksDirectorialDebut, Zhang Yimou’s feature directorial debut]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: marksDirectorialDebut Context triple: [Red Sorghum, marksDirectorialDebut, Zhang Yimou’s feature directorial debut]
-
A.
featureDirectorialDebutOf
chosen
Indicates that a work (typically a film) serves as the first directorial effort of a particular director.
-
B.
featureFilmDebut
Indicates that a work marks an entity’s first appearance or role in a feature-length film.
-
C.
filmDebut
Indicates the first film in which an entity (typically a person) appeared or participated, marking their initial entry into film work.
-
D.
filmDebutIn
Indicates the first film in which a person appeared or participated, marking their debut in cinema.
-
E.
screenDebutInFeatureFilmDirectionFor
Indicates that an entity made their first appearance as a director in a feature film for the specified work.
- F. None of above.
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_69d8b9ed3a2081909b2ec0d4dd2f4c37 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e47ad46a50819089c87f74efe3c7ca |
completed | April 19, 2026, 6:48 a.m. |
| PD | Predicate disambiguation | batch_69e3cde9dc288190af0e2198487f2051 |
completed | April 18, 2026, 6:31 p.m. |
Created at: April 10, 2026, 10:10 a.m.