Triple
T24861614
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haad Salad |
E622165
|
entity |
| Predicate | hasOnsiteService |
P95727
|
FINISHED |
| Object | dive and snorkel shops |
—
|
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: dive and snorkel shops | Statement: [Haad Salad, hasOnsiteService, dive and snorkel shops]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOnsiteService Context triple: [Haad Salad, hasOnsiteService, dive and snorkel shops]
-
A.
hasOnsiteFeature
Indicates that one entity possesses or includes a particular feature that is physically present at its location or premises.
-
B.
hasOnsiteLabel
Indicates that something is physically marked or identified with a label at its location or on its surface.
-
C.
hasOnsiteActivity
chosen
Indicates that an entity conducts or participates in activities that physically take place at a specific site or location.
-
D.
providesServiceOn
Indicates that one entity offers or performs a service during, on, or in connection with a specified time, date, or schedule.
-
E.
hasSupportService
Indicates that one entity provides or is associated with a support-related service for 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_69e2fac350d08190b3affde1b451a8c5 |
completed | April 18, 2026, 3:30 a.m. |
| NER | Named-entity recognition | batch_69f44a417a58819081777e18dda149fd |
completed | May 1, 2026, 6:37 a.m. |
| PD | Predicate disambiguation | batch_69f442b8479c8190a7c8e416ac9e28a0 |
completed | May 1, 2026, 6:05 a.m. |
Created at: April 18, 2026, 5:22 a.m.