Triple
T9917767
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ko Poda |
E185912
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Ko Mor |
E605449
|
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: Ko Mor | Statement: [Ko Poda, near, Ko Mor]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ko Mor Context triple: [Ko Poda, near, Ko Mor]
-
A.
Ko Muk
chosen
Ko Muk is a small Thai island in the Andaman Sea, known for its tranquil beaches and the famous Emerald Cave, a hidden lagoon accessible only by swimming through a sea tunnel.
-
B.
Koh
Koh is a Korean surname borne by various notable individuals across fields such as law, politics, and the arts.
-
C.
Koyasan
Koyasan is a sacred Buddhist monastic complex in Japan’s Wakayama Prefecture, renowned as the center of Shingon Buddhism and a major pilgrimage destination.
-
D.
Kume Island
Kume Island is a subtropical Japanese island in the East China Sea known for its scenic beaches, clear waters, and traditional Ryukyuan culture.
-
E.
Ko Tarutao
Ko Tarutao is a large, relatively undeveloped island in southern Thailand known for its rugged natural landscapes, wildlife, and role as a former prison site.
- 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_69ca829b45f481909040f7b99a1976ed |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cdb5673f108190914e0c172dddc65f |
completed | April 2, 2026, 12:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d20dec42848190ab9f8663155df83f |
completed | April 5, 2026, 7:23 a.m. |
Created at: March 30, 2026, 8:42 p.m.