Triple
T13255360
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lamma Island |
E315643
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Mo Tat Wan
Mo Tat Wan is a small, tranquil coastal village on Hong Kong’s Lamma Island known for its beach and relaxed, rural atmosphere.
|
E1030504
|
NE FINISHED |
How this triple was built (4 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: Mo Tat Wan | Statement: [Lamma Island, hasSettlement, Mo Tat Wan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mo Tat Wan Context triple: [Lamma Island, hasSettlement, Mo Tat Wan]
-
A.
Ma Tau Kok
Ma Tau Kok is a residential and industrial area in eastern Kowloon, Hong Kong, known for its waterfront location and mix of older housing estates and commercial developments.
-
B.
Tai Khuen
Tai Khuen is a Tai ethnic group and language primarily associated with the Kengtung region of eastern Myanmar.
-
C.
Sha Tau Kok
Sha Tau Kok is a frontier town in northeastern Hong Kong known for its restricted border area status and proximity to the boundary with mainland China.
-
D.
Haad Tien
Haad Tien is a quiet, scenic beach on Thailand’s Ko Pha Ngan island, known for its relaxed atmosphere, clear waters, and natural surroundings.
-
E.
Mou Tapu
Mou Tapu is a small, scenic island located within Lake Wanaka in New Zealand’s South Island, known for its natural beauty and cultural significance.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mo Tat Wan Triple: [Lamma Island, hasSettlement, Mo Tat Wan]
Generated description
Mo Tat Wan is a small, tranquil coastal village on Hong Kong’s Lamma Island known for its beach and relaxed, rural atmosphere.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mo Tat Wan Target entity description: Mo Tat Wan is a small, tranquil coastal village on Hong Kong’s Lamma Island known for its beach and relaxed, rural atmosphere.
-
A.
Ma Tau Kok
Ma Tau Kok is a residential and industrial area in eastern Kowloon, Hong Kong, known for its waterfront location and mix of older housing estates and commercial developments.
-
B.
Tai Khuen
Tai Khuen is a Tai ethnic group and language primarily associated with the Kengtung region of eastern Myanmar.
-
C.
Sha Tau Kok
Sha Tau Kok is a frontier town in northeastern Hong Kong known for its restricted border area status and proximity to the boundary with mainland China.
-
D.
Haad Tien
Haad Tien is a quiet, scenic beach on Thailand’s Ko Pha Ngan island, known for its relaxed atmosphere, clear waters, and natural surroundings.
-
E.
Mou Tapu
Mou Tapu is a small, scenic island located within Lake Wanaka in New Zealand’s South Island, known for its natural beauty and cultural significance.
- F. None of above. chosen
Provenance (5 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_69d806b1072881909e46bd212259c5f0 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d98f7517048190b4eac4e44e81ff66 |
completed | April 11, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a4240d881909f0ee898fd272826 |
completed | May 3, 2026, 8:41 a.m. |
| NEDg | Description generation | batch_69f70c9718d08190b09fc6723712ef55 |
completed | May 3, 2026, 8:51 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f70d32b38881909d500b81a0164bda |
completed | May 3, 2026, 8:54 a.m. |
Created at: April 9, 2026, 9:24 p.m.