Triple
T4459788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Police Story 2013 |
E98222
|
entity |
| Predicate | releaseDateChina |
P56661
|
FINISHED |
| Object | 2013-12-24 |
—
|
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: 2013-12-24 | Statement: [Police Story 2013, releaseDateChina, 2013-12-24]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: releaseDateChina Context triple: [Police Story 2013, releaseDateChina, 2013-12-24]
-
A.
releaseDateSouthKorea
Indicates the date on which something (such as a product, film, or work) was officially released in South Korea.
-
B.
releaseDateUS
Indicates the date on which something is officially released or made available in the United States.
-
C.
releaseDateRestOfWorld
Indicates the date on which something is released or made available outside its primary or initial country or region, i.e., in the rest of the world.
-
D.
releaseDateJapan
Indicates the date on which something is officially released or made available in Japan.
-
E.
releaseDateUnitedKingdom
Indicates the date on which something (such as a product, work, or event) was officially released or made available in the United Kingdom.
- F. None of above. chosen
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_69b3454a7c608190944f5455c8031d73 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b3567184f481908a2787e4ac9bb345 |
completed | March 13, 2026, 12:12 a.m. |
| PD | Predicate disambiguation | batch_69b34f649df081909d3cc2f6a1b8f282 |
completed | March 12, 2026, 11:42 p.m. |
| PDg | Predicate description generation | batch_69b354e1f0948190b645096b2b7037af |
completed | March 13, 2026, 12:05 a.m. |
Created at: March 12, 2026, 11:33 p.m.