Triple
T6815001
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tybee Island beaches |
E156729
|
entity |
| Predicate | haveAmenity |
P5622
|
FINISHED |
| Object | public beach access points with boardwalks |
—
|
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: public beach access points with boardwalks | Statement: [Tybee Island beaches, haveAmenity, public beach access points with boardwalks]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: haveAmenity Context triple: [Tybee Island beaches, haveAmenity, public beach access points with boardwalks]
-
A.
hasAmenityAccessTo
Indicates that an entity has the right or ability to use or benefit from a specified amenity or facility.
-
B.
amenity
chosen
Indicates that one entity provides a useful facility, service, or feature that enhances the convenience or comfort of another entity.
-
C.
amenityLevel
Indicates the degree or quality of facilities, services, or conveniences provided in relation to something.
-
D.
hasDiningFeature
Indicates that something possesses a specific characteristic, amenity, or attribute related to dining.
-
E.
hasFacilityType
Indicates that an entity possesses or is associated with a specific type or category of facility.
- 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_69c68828b26c819090fe9df7612bbc27 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d32c40508190932718a649fc1417 |
completed | March 27, 2026, 6:57 p.m. |
| PD | Predicate disambiguation | batch_69c6d09bb4f881909bf20c188cb3e8e1 |
completed | March 27, 2026, 6:46 p.m. |
Created at: March 27, 2026, 2:17 p.m.