Triple
T17091530
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | North Hamgyong Province |
E414737
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object |
Rason
Rason is a North Korean special economic zone and port city in the country’s northeast, known for its strategic location near the borders with China and Russia.
|
E1249727
|
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: Rason | Statement: [North Hamgyong Province, hasMajorCity, Rason]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rason Context triple: [North Hamgyong Province, hasMajorCity, Rason]
-
A.
Brule
Brule is a small coastal community in Nova Scotia, Canada, known for its rural setting and proximity to the Northumberland Strait.
-
B.
Larimore
Larimore is a small city in eastern North Dakota, United States, known for its rural character and proximity to Grand Forks.
-
C.
Kolda
Kolda is a regional city in southern Senegal, known as an important administrative and commercial center in the Casamance area.
-
D.
Zunheboto
Zunheboto is a town in the northeastern Indian state of Nagaland, known as the headquarters of the Sumi Naga community and for its hilly terrain and rich tribal culture.
-
E.
Rangeli
Rangeli is a prominent town in southeastern Nepal that serves as an important local commercial and administrative center in Morang District.
- 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: Rason Triple: [North Hamgyong Province, hasMajorCity, Rason]
Generated description
Rason is a North Korean special economic zone and port city in the country’s northeast, known for its strategic location near the borders with China and Russia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rason Target entity description: Rason is a North Korean special economic zone and port city in the country’s northeast, known for its strategic location near the borders with China and Russia.
-
A.
Brule
Brule is a small coastal community in Nova Scotia, Canada, known for its rural setting and proximity to the Northumberland Strait.
-
B.
Larimore
Larimore is a small city in eastern North Dakota, United States, known for its rural character and proximity to Grand Forks.
-
C.
Kolda
Kolda is a regional city in southern Senegal, known as an important administrative and commercial center in the Casamance area.
-
D.
Zunheboto
Zunheboto is a town in the northeastern Indian state of Nagaland, known as the headquarters of the Sumi Naga community and for its hilly terrain and rich tribal culture.
-
E.
Rangeli
Rangeli is a prominent town in southeastern Nepal that serves as an important local commercial and administrative center in Morang District.
- 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_69d886cfc8e88190b05ba466edd35591 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3dbfa09b08190be4303dd0d174feb |
completed | April 18, 2026, 7:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a012ee9fd108190b12e8624bb66caf2 |
completed | May 11, 2026, 1:20 a.m. |
| NEDg | Description generation | batch_6a012fe2a1b081909483baef845cc2c1 |
completed | May 11, 2026, 1:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0130c2ad9881909d8a8b64ebb59aa6 |
completed | May 11, 2026, 1:28 a.m. |
Created at: April 10, 2026, 5:35 a.m.