Triple
T8934238
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ke‘anae |
E212736
|
entity |
| Predicate | isStopOn |
P9950
|
FINISHED |
| Object | Hana Highway |
E62619
|
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: Hana Highway | Statement: [Ke‘anae, isStopOn, Hana Highway]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hana Highway Context triple: [Ke‘anae, isStopOn, Hana Highway]
-
A.
Hana Highway
chosen
Hana Highway is a famously scenic, winding coastal road on the island of Maui in Hawaii, known for its lush rainforests, waterfalls, and dramatic ocean views.
-
B.
Keiji Bypass
Keiji Bypass is a major expressway in Japan that serves as a key bypass route around the Kyoto–Osaka area to alleviate traffic congestion and improve regional connectivity.
-
C.
Ikuta Road
Ikuta Road is a popular shopping and entertainment street in Kobe’s Sannomiya district, known for its dense mix of boutiques, restaurants, and nightlife spots.
-
D.
Akagi Panorama Road
Akagi Panorama Road is a scenic mountain roadway in Japan known for its winding route and expansive views around Mount Akagi.
-
E.
Fujin Road
Fujin Road is a metro station in Shanghai, China, serving as the northern terminus of Line 1 of the Shanghai Metro system.
- 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_69ca8395c438819087d7cb844ab5990c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc669138b48190a6bb4968f029a69e |
completed | April 1, 2026, 12:28 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfc1ddac548190bf520321dd35de1c |
completed | April 3, 2026, 1:34 p.m. |
Created at: March 30, 2026, 6:57 p.m.