Triple
T20588770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pohang |
E505857
|
entity |
| Predicate | hasSubdivision |
P747
|
FINISHED |
| Object |
Buk-gu
Buk-gu is a northern district of the coastal city of Pohang in South Korea, known for its industrial facilities and residential areas.
|
E1446646
|
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: Buk-gu | Statement: [Pohang, hasSubdivision, Buk-gu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Buk-gu Context triple: [Pohang, hasSubdivision, Buk-gu]
-
A.
Buk-gu
Buk-gu is a northern administrative district of the metropolitan city of Ulsan in South Korea.
-
B.
Buk-gu
Buk-gu is a northern administrative district of Daegu, South Korea, known for its residential neighborhoods, educational institutions, and commercial areas.
-
C.
Buk-gu
Buk-gu is a northern district of Busan, South Korea, known as an urban residential and commercial area within the metropolitan city.
-
D.
Bokpyin
Bokpyin is a coastal town in southern Myanmar known for its location near the Andaman Sea and its role in regional fishing and trade.
-
E.
Donggureung
Donggureung is a large royal burial complex in Guri, South Korea, containing multiple tombs of Joseon Dynasty kings and queens and recognized as part of a UNESCO World Heritage site.
- 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: Buk-gu Triple: [Pohang, hasSubdivision, Buk-gu]
Generated description
Buk-gu is a northern district of the coastal city of Pohang in South Korea, known for its industrial facilities and residential areas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Buk-gu Target entity description: Buk-gu is a northern district of the coastal city of Pohang in South Korea, known for its industrial facilities and residential areas.
-
A.
Buk-gu
Buk-gu is a northern administrative district of the metropolitan city of Ulsan in South Korea.
-
B.
Buk-gu
Buk-gu is a northern administrative district of Daegu, South Korea, known for its residential neighborhoods, educational institutions, and commercial areas.
-
C.
Buk-gu
Buk-gu is a northern district of Busan, South Korea, known as an urban residential and commercial area within the metropolitan city.
-
D.
Bokpyin
Bokpyin is a coastal town in southern Myanmar known for its location near the Andaman Sea and its role in regional fishing and trade.
-
E.
Donggureung
Donggureung is a large royal burial complex in Guri, South Korea, containing multiple tombs of Joseon Dynasty kings and queens and recognized as part of a UNESCO World Heritage site.
- 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_69e0b4b9669c8190b8e81fc72817d42c |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a979e4a48190a948165fb0f3b265 |
completed | April 20, 2026, 10:32 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08e03ece3c819082903861a63e21a7 |
completed | May 16, 2026, 9:23 p.m. |
| NEDg | Description generation | batch_6a08e0e44be8819081e3ee727887802e |
completed | May 16, 2026, 9:25 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08e18faf24819092098e3b74a418e1 |
completed | May 16, 2026, 9:28 p.m. |
Created at: April 16, 2026, 11:40 a.m.