Triple
T12830510
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Heʻeia |
E306770
|
entity |
| Predicate | adjacentTo |
P224
|
FINISHED |
| Object | Kāneʻohe |
E59567
|
NE 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: Kāneʻohe | Statement: [Heʻeia, adjacentTo, Kāneʻohe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kāneʻohe Context triple: [Heʻeia, adjacentTo, Kāneʻohe]
-
A.
Kaneohe
chosen
Kaneohe is a residential town on the windward side of Oahu in Hawaii, known for its lush landscapes, views of the Koʻolau Mountains, and access to Kaneohe Bay.
-
B.
Kakaʻako
Kakaʻako is a rapidly redeveloping urban neighborhood in Honolulu known for its high-rise condos, vibrant street art, and waterfront parks.
-
C.
Waialae
Waialae is a residential neighborhood in Honolulu, Hawaii, known for its proximity to Waikiki and the upscale Kahala area.
-
D.
Wailuku
Wailuku is a historic town on the Hawaiian island of Maui that serves as the county seat and a cultural and administrative center.
-
E.
Waimānalo
Waimānalo is a coastal community on the windward side of Oʻahu in Hawaiʻi, known for its long sandy beach, rural character, and strong Native Hawaiian presence.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96faf9ae481908265e198f917d1e6 |
completed | April 10, 2026, 9:46 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7b8be7834819085bfce037c467004 |
completed | May 3, 2026, 9:06 p.m. |
Created at: April 9, 2026, 5:34 p.m.