Triple
T8985980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Koki Beach |
E214664
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Hāna |
E214001
|
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: Hāna | Statement: [Koki Beach, locatedIn, Hāna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hāna Context triple: [Koki Beach, locatedIn, Hāna]
-
A.
Hāna
chosen
Hāna is a small, remote town on the eastern coast of Maui, Hawaii, known for its lush landscapes, scenic coastal views, and the famously winding Road to Hāna.
-
B.
Kihei
Kihei is a coastal town on the southwest shore of Maui, Hawaii, known for its sunny weather, beaches, and resort and residential communities.
-
C.
Kalaheo
Kalaheo is a small residential community on the island of Kauai in Hawaii, known for its hillside neighborhoods, coffee farms, and views over the island’s south shore.
-
D.
Līhuʻe
Līhuʻe is the principal town and administrative center of Kauai County on the Hawaiian island of Kauai.
-
E.
Lihue
Lihue is the county seat and main commercial center of the Hawaiian island of Kauai, known for its airport, harbor, and role as a gateway for visitors.
- 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_69ca839f76bc8190a4b7123cdd682199 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc67eddbf08190afca16e0be435241 |
completed | April 1, 2026, 12:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfd0bdb05c8190bb1fb5f0272a450a |
completed | April 3, 2026, 2:37 p.m. |
Created at: March 30, 2026, 7:03 p.m.