Triple
T36921413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | MK2 Diffusion |
E913209
|
entity |
| Predicate | notableReleaseDirector |
P98246
|
FINISHED |
| Object | Krzysztof Kieślowski |
E270915
|
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: Krzysztof Kieślowski | Statement: [MK2 Diffusion, notableReleaseDirector, Krzysztof Kieślowski]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: notableReleaseDirector Context triple: [MK2 Diffusion, notableReleaseDirector, Krzysztof Kieślowski]
-
A.
notableDirector
Indicates that a person has directed a work (such as a film or show) in a way that is recognized as significant or distinguished.
-
B.
notableProductionDirector
chosen
Indicates that a person served as a significant or distinguished director for a particular production.
-
C.
notableRelease
Indicates that an entity is a significant or prominent release (such as a major version, edition, or launch) associated with another entity.
-
D.
notableDirectorUser
Indicates that the user is recognized as a notable or distinguished film director.
-
E.
notableTitleReleaseYear
Indicates the year in which a notable work or title associated with an entity was released.
- F. None of above.
Provenance (4 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_69f76e885b848190bad82c87e9525486 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a037c8e2c648190a65fc9c7872861af |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a4076de03388190b70d254b57c82294 |
completed | June 28, 2026, 1:20 a.m. |
| PD | Predicate disambiguation | batch_6a037a10036481909c71188b2a0e7f04 |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:13 p.m.