Triple
T3702963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kihei |
E80823
|
entity |
| Predicate | island |
P970
|
FINISHED |
| Object | Maui |
E15811
|
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: Maui | Statement: [Kihei, island, Maui]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maui Context triple: [Kihei, island, Maui]
-
A.
Maui
chosen
Maui is a major Hawaiian island renowned for its scenic beaches, volcanic landscapes, and rich native Hawaiian culture.
-
B.
Lānaʻi
Lānaʻi is one of the smaller inhabited Hawaiian Islands, known for its quiet, rural character and luxury resort tourism.
-
C.
Molokaʻi
Molokaʻi is one of the major Hawaiian Islands, known for its relatively undeveloped landscape, strong Native Hawaiian culture, and dramatic sea cliffs.
-
D.
Oahu
Oahu is a major Hawaiian island known for its capital city Honolulu, iconic Waikiki Beach, and significant World War II history.
-
E.
Big Island
Big Island is a notable large island located within Lake of the Woods, a lake that spans the borders of Minnesota, Manitoba, and Ontario.
- 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_69ad8b1793888190a5f70e4b21dc05a1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69adc54925b48190b23d2a14ef825abc |
completed | March 8, 2026, 6:51 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b65082ca248190bfe7350ccc6b6b6a |
completed | March 15, 2026, 6:24 a.m. |
Created at: March 8, 2026, 3:33 p.m.