Triple
T11202577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Killing of a Chinese Bookie |
E265075
|
entity |
| Predicate | hasTheatricalRelease |
P38679
|
FINISHED |
| Object | 1976 |
—
|
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: 1976 | Statement: [The Killing of a Chinese Bookie, hasTheatricalRelease, 1976]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasTheatricalRelease Context triple: [The Killing of a Chinese Bookie, hasTheatricalRelease, 1976]
-
A.
theatricalReleaseWith
Indicates that two or more entities share the same theatrical release context, such as being released together or as part of the same theatrical event or distribution.
-
B.
hasTheatricalForm
Indicates that something is associated with or presented in a particular theatrical form or style.
-
C.
theatricalReleaseIn
Indicates that a film or performance was released or shown theatrically in a specified location or market.
-
D.
servedInTheatres
Indicates that a film or performance was publicly exhibited in movie theaters or similar cinema venues.
-
E.
releaseDate_Theatrical
chosen
Indicates the date on which a work was first made publicly available in theaters.
- 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_69d6aa9eb9248190b20211772621b4bc |
completed | April 8, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69d7e8c36c188190bfa4d5f8e6cbbbea |
completed | April 9, 2026, 5:58 p.m. |
| PD | Predicate disambiguation | batch_69d75cf83464819087529d47d025d313 |
completed | April 9, 2026, 8:02 a.m. |
Created at: April 8, 2026, 9:29 p.m.