Triple
T35836611
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 吳彥祖 |
E1035956
|
entity |
| Predicate | 主要工作地 |
P148956
|
FINISHED |
| Object | 香港 |
—
|
NE NERFINISHED |
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 | Statement: [吳彥祖, 主要工作地, 香港]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 主要工作地 Context triple: [吳彥祖, 主要工作地, 香港]
-
A.
locationOfWork
Indicates the place or site where an entity performs its work or carries out its professional activities.
-
B.
residesInWork
Indicates that a person or entity lives or is based within the location, setting, or environment defined by a particular work (such as a book, film, or other creative piece).
-
C.
residenceInWork
Indicates that an entity’s place of residence is located within or at the same site as their place of work.
-
D.
workedPrimarilyIn
chosen
Indicates that an entity carried out the majority of its work, activity, or career within a particular field, location, or context.
-
E.
locationInWork
Indicates that one entity specifies the place or setting where another entity occurs, is situated, or takes place within a particular work (e.g., a scene’s location in a film or a chapter’s setting in a book).
- 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_69f76e192a94819082db360cb91e6a8d |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7aa699d68819081ed363931894ab3 |
completed | May 3, 2026, 8:04 p.m. |
| PD | Predicate disambiguation | batch_69f7a8d219f8819081dc4ce3c83ca0cb |
completed | May 3, 2026, 7:58 p.m. |
Created at: May 3, 2026, 4:06 p.m.