Triple
T23259737
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Masan |
E581969
|
entity |
| Predicate | romanization |
P2508
|
FINISHED |
| Object | Masan-si |
—
|
NE NERFINISHED |
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: Masan-si | Statement: [Masan, romanization, Masan-si]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Masan-si Context triple: [Masan, romanization, Masan-si]
-
A.
Masan
chosen
Masan is a city in South Korea that serves as a regional administrative and judicial center, hosting a seat of the country's district courts.
-
B.
Odaesan
Odaesan is a prominent mountain in South Korea known for its scenic national park, rich biodiversity, and important Buddhist temples such as Woljeongsa.
-
C.
Sunam
Sunam is a town in the Sangrur district of Punjab, India, known as the birthplace of Indian revolutionary Udham Singh.
-
D.
Sariwon
Sariwon is a major city in southwestern North Korea known as an administrative, transportation, and agricultural center.
-
E.
Manan-gu
Manan-gu is a district-level administrative area within the city of Anyang in Gyeonggi Province, South Korea.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e246079f58819085eaa9c260906880 |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f194c7ec148190b01fd215a0c1daa1 |
completed | April 29, 2026, 5:19 a.m. |
Created at: April 17, 2026, 4:11 p.m.