Triple
T7238102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ko Samui |
E155281
|
entity |
| Predicate | hasNearbyIsland |
P970
|
FINISHED |
| Object |
Ko Matsum
Ko Matsum is a small, tranquil island near Ko Samui in Thailand, known for its quiet beaches and relatively undeveloped, natural atmosphere.
|
E650727
|
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: Ko Matsum | Statement: [Ko Samui, hasNearbyIsland, Ko Matsum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ko Matsum Context triple: [Ko Samui, hasNearbyIsland, Ko Matsum]
-
A.
Hyakutake
Hyakutake is a Japanese surname borne by several notable individuals, including military figures and other public personalities.
-
B.
Kuwahi
Kuwahi is the Cherokee name for Clingmans Dome, the highest peak in Great Smoky Mountains National Park and one of the tallest mountains in the eastern United States.
-
C.
Raikō-tō
Raikō-tō is the Japanese name for Raikoke, an uninhabited volcanic island in Russia’s Kuril Islands chain known for its explosive eruptions.
-
D.
Kurohime-yama
Kurohime-yama is a subsidiary peak of Japan’s Mount Akagi, known as part of the volcanic mountain’s multi-summit range in Gunma Prefecture.
-
E.
Kurohime-yama
Kurohime-yama is a mountain in Japan, known for its scenic landscapes and popular hiking and skiing opportunities.
- 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: Ko Matsum Triple: [Ko Samui, hasNearbyIsland, Ko Matsum]
Generated description
Ko Matsum is a small, tranquil island near Ko Samui in Thailand, known for its quiet beaches and relatively undeveloped, natural atmosphere.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ko Matsum Target entity description: Ko Matsum is a small, tranquil island near Ko Samui in Thailand, known for its quiet beaches and relatively undeveloped, natural atmosphere.
-
A.
Hyakutake
Hyakutake is a Japanese surname borne by several notable individuals, including military figures and other public personalities.
-
B.
Kuwahi
Kuwahi is the Cherokee name for Clingmans Dome, the highest peak in Great Smoky Mountains National Park and one of the tallest mountains in the eastern United States.
-
C.
Raikō-tō
Raikō-tō is the Japanese name for Raikoke, an uninhabited volcanic island in Russia’s Kuril Islands chain known for its explosive eruptions.
-
D.
Kurohime-yama
Kurohime-yama is a subsidiary peak of Japan’s Mount Akagi, known as part of the volcanic mountain’s multi-summit range in Gunma Prefecture.
-
E.
Kurohime-yama
Kurohime-yama is a mountain in Japan, known for its scenic landscapes and popular hiking and skiing opportunities.
- 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_69c688143bfc81908d4176617735e601 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ea368fb88190bd9e991e8b94dac6 |
completed | March 27, 2026, 8:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7cc381a4081909a8ea7ee02348328 |
completed | March 28, 2026, 12:40 p.m. |
| NEDg | Description generation | batch_69c7cda71c088190afe117d8d3ff04ab |
completed | March 28, 2026, 12:46 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c7ce1b5e0081908d8e68fb1c0bfd3e |
completed | March 28, 2026, 12:48 p.m. |
Created at: March 27, 2026, 2:55 p.m.