Triple
T14627863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tsuen Wan |
E343399
|
entity |
| Predicate | majorIslandNearby |
P19485
|
FINISHED |
| Object | Ma Wan |
E314092
|
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: Ma Wan | Statement: [Tsuen Wan, majorIslandNearby, Ma Wan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ma Wan Context triple: [Tsuen Wan, majorIslandNearby, Ma Wan]
-
A.
Ma Wan
chosen
Ma Wan is a small island in Hong Kong known for its residential developments, historic fishing village, and attractions like Noah’s Ark near the Tsing Ma Bridge.
-
B.
Long Ke Wan
Long Ke Wan is a remote, crescent-shaped white-sand beach in Hong Kong’s Sai Kung area, known for its clear waters, dramatic coastal scenery, and popularity with hikers and campers.
-
C.
Tai Hang
Tai Hang is a residential and dining neighborhood on Hong Kong Island known for its narrow streets, local eateries, and the annual Fire Dragon Dance during the Mid-Autumn Festival.
-
D.
Sok Kwu Wan
Sok Kwu Wan is a traditional fishing village and popular seafood and hiking destination on Lamma Island in Hong Kong.
-
E.
Peng Chau
Peng Chau is a small, laid-back outlying island of Hong Kong known for its traditional villages, temples, and coastal scenery.
- 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_69d822dffc3c8190aa173b90761bffda |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4a7c8fc81909d10c1f563d7d1e7 |
completed | April 14, 2026, 9:41 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdf078c1248190889ce04cffbf51dc |
completed | May 8, 2026, 2:17 p.m. |
Created at: April 10, 2026, 1:26 a.m.