Triple
T32331082
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hotel H2O |
E826051
|
entity |
| Predicate | offersDirectAccessTo |
P68242
|
FINISHED |
| Object | Manila Ocean Park attractions |
—
|
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: Manila Ocean Park attractions | Statement: [Hotel H2O, offersDirectAccessTo, Manila Ocean Park attractions]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: offersDirectAccessTo Context triple: [Hotel H2O, offersDirectAccessTo, Manila Ocean Park attractions]
-
A.
offersAccessVia
Indicates that one entity provides a means or channel through which another entity can be accessed or utilized.
-
B.
offersAccess
chosen
Indicates that one entity provides another entity with the ability or permission to use, enter, or interact with a resource, service, or location.
-
C.
offersServiceTo
Indicates that one entity provides or makes a service available for the benefit or use of another entity.
-
D.
hasDirectServices
Indicates that one entity provides services directly to another entity without intermediaries.
-
E.
notDirectlyAvailableFor
Indicates that an entity cannot be accessed, used, or obtained immediately or without intermediaries, but may be reachable through indirect means or additional steps.
- 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_69f34913d9048190befaa634025232be |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69fd64bc86848190a49f451a8fc5cf1e |
completed | May 8, 2026, 4:21 a.m. |
| PD | Predicate disambiguation | batch_69fd5ff4a648819090756d90fd195d9a |
completed | May 8, 2026, 4 a.m. |
Created at: May 1, 2026, 12:47 a.m.