Triple
T38702815
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Haʻikū Stairs |
E950184
|
entity |
| Predicate | accessPointNearby |
P191767
|
FINISHED |
| Object | Kaneohe |
—
|
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: Kaneohe | Statement: [Haʻikū Stairs, accessPointNearby, Kaneohe]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: accessPointNearby Context triple: [Haʻikū Stairs, accessPointNearby, Kaneohe]
-
A.
accessPointRegion
Indicates the geographic or spatial region within which a given access point is located or operates.
-
B.
popularAccessPointsInclude
Indicates that certain commonly used or frequently chosen access points are part of, or contained within, a specified set or collection of access points.
-
C.
modernAccessPoint
Indicates that an entity serves as a contemporary or up-to-date point of entry, connection, or interaction for accessing another entity or resource.
-
D.
isAccessPointOf
Indicates that one entity serves as an access point or entry interface through which another entity can be reached, used, or connected to.
-
E.
bestAccessPoint
Indicates that one access point is considered the most suitable or optimal choice for connecting to a given entity or location among available alternatives.
- F. None of above. chosen
Provenance (4 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_69f76f0124408190bb39c3040734846b |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fcea52dc6c81909ff3106790f3f346 |
completed | May 7, 2026, 7:38 p.m. |
| PD | Predicate disambiguation | batch_69fce5b66de88190a2bd19665a699a3d |
completed | May 7, 2026, 7:19 p.m. |
| PDg | Predicate description generation | batch_69fcea51ea908190b7895045b8a15115 |
completed | May 7, 2026, 7:38 p.m. |
Created at: May 3, 2026, 4:33 p.m.