Triple
T23282311
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jia Zhangke |
E588896
|
entity |
| Predicate | dateOfFirstFeatureFilm |
P65899
|
FINISHED |
| Object | 1997 |
—
|
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: 1997 | Statement: [Jia Zhangke, dateOfFirstFeatureFilm, 1997]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: dateOfFirstFeatureFilm Context triple: [Jia Zhangke, dateOfFirstFeatureFilm, 1997]
-
A.
firstUsedInFeatureFilm
Indicates that something (such as a technique, character, or element) made its earliest appearance or application in a particular feature film.
-
B.
firstFeatureFilmRelease
chosen
Indicates the date or event of an entity’s debut feature-length film being publicly released.
-
C.
earlyFilmsProducedBy
Indicates that the subject entity’s early films were produced by the object entity.
-
D.
firstFeatureAnimatedFilm
Indicates that the subject is the first animated feature film associated with, or fulfilling a particular role or distinction for, the object.
-
E.
firstFilmed
Indicates that one entity is the earliest or initial subject to be captured on film in relation to another entity or context.
- 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_69e25d16e2c08190a291de254703129e |
completed | April 17, 2026, 4:17 p.m. |
| NER | Named-entity recognition | batch_69f19643b8908190a2c29552b272dc61 |
completed | April 29, 2026, 5:25 a.m. |
| PD | Predicate disambiguation | batch_69effcecabd88190856fb6e1d993e4dd |
completed | April 28, 2026, 12:18 a.m. |
Created at: April 17, 2026, 4:58 p.m.