Triple
T14372112
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Geoje |
E356381
|
entity |
| Predicate | hasRevisedRomanization |
P23170
|
FINISHED |
| Object | Geoje-si |
E356381
|
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: Geoje-si | Statement: [Geoje, hasRevisedRomanization, Geoje-si]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geoje-si Context triple: [Geoje, hasRevisedRomanization, Geoje-si]
-
A.
Geoje
chosen
Geoje is a South Korean island city in South Gyeongsang Province known for its major shipbuilding industry and coastal scenery.
-
B.
oge
oge is the ISO 639-3 code for Old Georgian, the historical Kartvelian language used in early Georgian literature and religious texts.
-
C.
Geoemyda
Geoemyda is a small genus of Asian forest-dwelling turtles known for their terrestrial habits and preference for humid, shaded environments.
-
D.
The World: Geo Quiz
The World: Geo Quiz is a recurring geography trivia segment from the public radio program "The World," challenging listeners to identify global locations through clues about culture, history, and current events.
-
E.
Geyve
Geyve is a town and district in northwestern Turkey known for its agricultural production, especially fruit growing, within Sakarya Province.
- 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_69d8279163a081908aec45c0e3f1e02f |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8fb2082c8190b42cc5f2bab4f574 |
completed | April 14, 2026, 7:04 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd551002948190aeb93d245e1449a7 |
completed | May 8, 2026, 3:14 a.m. |
Created at: April 10, 2026, 1:15 a.m.