Triple
T17776524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hana Highway |
E443783
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object | Hawaii Route 36 |
E220336
|
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: Hawaii Route 36 | Statement: [Hana Highway, partOf, Hawaii Route 36]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hawaii Route 36 Context triple: [Hana Highway, partOf, Hawaii Route 36]
-
A.
Hawaii Route 36
chosen
Hawaii Route 36 is a state highway on the island of Maui that forms part of the scenic coastal roadway connecting Kahului to the Hāna region.
-
B.
Hawaii Route 31
Hawaii Route 31 is a state highway on the island of Maui that runs along the island’s southeastern coast, providing access to rural communities and scenic coastal areas.
-
C.
Hawaii Route 37
Hawaii Route 37 is a state highway on the island of Maui that connects Kahului to the upcountry and southeastern regions, including Pukalani, Kula, and Ulupalakua.
-
D.
Hawaii Route 35
Hawaii Route 35 is a state highway in Hawaii that serves as part of the local numbered route network on one of the islands.
-
E.
Hawaii Route 32
Hawaii Route 32 is a state highway on the island of Maui that serves the town of Wailuku and connects it to surrounding areas.
- 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_69d8b9ef17708190bdf7e2adbf14ddc2 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4871d43a481908aacde69bd8091b0 |
completed | April 19, 2026, 7:41 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a02f8321e288190be4228b6975f372d |
completed | May 12, 2026, 9:51 a.m. |
Created at: April 10, 2026, 10:12 a.m.