Triple
T35798180
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cheung Po Tsai Cave |
E1034892
|
entity |
| Predicate | visitorAdvice |
P64322
|
FINISHED |
| Object | visitors often bring flashlights |
—
|
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: visitors often bring flashlights | Statement: [Cheung Po Tsai Cave, visitorAdvice, visitors often bring flashlights]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visitorAdvice Context triple: [Cheung Po Tsai Cave, visitorAdvice, visitors often bring flashlights]
-
A.
visitorService
Indicates a relationship where a service is provided specifically for or to visitors, such as assistance, information, or support during their visit.
-
B.
visitorPractice
chosen
Indicates that a visitor engages in or performs a particular practice, activity, or routine.
-
C.
visitorUse
Indicates that an entity is being used, accessed, or engaged with by a visitor or temporary user.
-
D.
visitorGuideline
Indicates guidelines or rules that specify how visitors are expected or allowed to behave or proceed in a particular context.
-
E.
visitorIs
Indicates that one entity is acting in the role or capacity of a visitor with respect to another entity.
- 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_69f76e169bd081909f16cd8c9ee7870c |
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.