Triple
T17024798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hong Kong Film Award for Best Actor |
E413034
|
entity |
| Predicate | awardNameInChinese |
P109381
|
FINISHED |
| Object | 香港電影金像獎最佳男主角 |
—
|
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: 香港電影金像獎最佳男主角 | Statement: [Hong Kong Film Award for Best Actor, awardNameInChinese, 香港電影金像獎最佳男主角]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: awardNameInChinese Context triple: [Hong Kong Film Award for Best Actor, awardNameInChinese, 香港電影金像獎最佳男主角]
-
A.
awardName
Indicates the specific name or title of an award associated with an entity.
-
B.
awardNameLanguage
Indicates the language in which the name of an award is expressed.
-
C.
awardNameIncludes
chosen
Indicates that the name of an award contains the specified text or substring.
-
D.
awardLocale
Indicates the place or geographic location where an award is given or recognized.
-
E.
awardLanguage
Indicates that an award is given specifically for works or achievements in a particular language.
- 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_69d886cc4170819093deddc7b8b4b6a7 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d5d371148190a60d32a72abec09a |
completed | April 18, 2026, 7:04 p.m. |
| PD | Predicate disambiguation | batch_69e35d5be7f48190af9db67a1e23850f |
completed | April 18, 2026, 10:30 a.m. |
Created at: April 10, 2026, 5:33 a.m.