Triple
T7071327
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Poʻipū |
E164702
|
entity |
| Predicate | hasNearbyArea |
P4647
|
FINISHED |
| Object | Kōloa |
E166964
|
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: Kōloa | Statement: [Poʻipū, hasNearbyArea, Kōloa]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kōloa Context triple: [Poʻipū, hasNearbyArea, Kōloa]
-
A.
Lēʻahi
Lēʻahi is the Hawaiian name for Diamond Head, the iconic volcanic tuff cone and landmark overlooking Waikīkī on the island of Oʻahu.
-
B.
Nānākuli
Nānākuli is a coastal community on the leeward side of Oʻahu in Hawaii, known for its strong Native Hawaiian presence and scenic beaches.
-
C.
Kapaʻa
chosen
Kapaʻa is a coastal town on the east side of the Hawaiian island of Kauaʻi known for its beaches, shops, and laid-back atmosphere.
-
D.
Lakona
Lakona is an Oceanic language of northern Vanuatu, spoken on the island of Gaua in the Banks Islands.
-
E.
Kailua
Kailua is a coastal town on the windward side of Oahu in Hawaii, known for its scenic beaches and relaxed residential atmosphere.
- 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_69c6887b96548190a8a9b3ac8adf4119 |
completed | March 27, 2026, 1:39 p.m. |
| NER | Named-entity recognition | batch_69c6e4c9cdbc8190b91cd3b4eef58eb6 |
completed | March 27, 2026, 8:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c810a6b5348190bdf98a2fd98c9dc5 |
completed | March 28, 2026, 5:32 p.m. |
Created at: March 27, 2026, 2:39 p.m.