Triple
T16467112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoje Island |
E399961
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Gohyeon |
E1100194
|
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: Gohyeon | Statement: [Geoje Island, hasSettlement, Gohyeon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gohyeon Context triple: [Geoje Island, hasSettlement, Gohyeon]
-
A.
Gohyeon
chosen
Gohyeon is the main urban and administrative center of Geoje, a city located on Geoje Island in South Gyeongsang Province, South Korea.
-
B.
Soyeon
Soyeon is a Korean-born interpreter and the wife of former German Chancellor Gerhard Schröder.
-
C.
Kun-hee
Kun-hee is the given name of Lee Kun-hee, the influential South Korean businessman who transformed Samsung into a global technology leader.
-
D.
Jinwicheon
Jinwicheon is a river flowing through the city of Pyeongtaek in South Korea.
-
E.
Ji-Yoon
Ji-Yoon is a Korean given name that can be used for people of any gender, though it is more commonly given to women.
- 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_69d87f2dac988190b74d6e185fa88ba4 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e32dcd707081908fb7ca91a8c09e0a |
completed | April 18, 2026, 7:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a004f5914dc81908c3b8cf999ee76a1 |
completed | May 10, 2026, 9:26 a.m. |
Created at: April 10, 2026, 5:11 a.m.