Triple
T6578729
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ʻEua |
E157237
|
entity |
| Predicate | partOf |
P40
|
FINISHED |
| Object |
ʻEua District
ʻEua District is an administrative division of Tonga that encompasses the island of ʻEua and its surrounding areas.
|
E607722
|
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: ʻEua District | Statement: [ʻEua, partOf, ʻEua District]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: ʻEua District Context triple: [ʻEua, partOf, ʻEua District]
-
A.
Kaʻū District
Kaʻū District is a large, rural region on the southern side of Hawaii’s Big Island, known for its volcanic landscapes, coffee farms, and rugged coastline.
-
B.
Manuʻa District
Manuʻa District is an administrative district of American Samoa encompassing the remote Manuʻa Islands in the eastern part of the territory.
-
C.
Kaliua District
Kaliua District is an administrative district located in western Tanzania, within the country’s Tabora Region.
-
D.
Naitasiri Province
Naitasiri Province is an inland province on the island of Viti Levu in Fiji, known for its rugged highlands, agriculture, and proximity to the capital city, Suva.
-
E.
Kīpahulu District
Kīpahulu District is a lush, coastal area on the eastern side of Maui known for its waterfalls, pools, and scenic hiking trails within Haleakalā National Park.
- 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: ʻEua District Triple: [ʻEua, partOf, ʻEua District]
Generated description
ʻEua District is an administrative division of Tonga that encompasses the island of ʻEua and its surrounding areas.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: ʻEua District Target entity description: ʻEua District is an administrative division of Tonga that encompasses the island of ʻEua and its surrounding areas.
-
A.
Kaʻū District
Kaʻū District is a large, rural region on the southern side of Hawaii’s Big Island, known for its volcanic landscapes, coffee farms, and rugged coastline.
-
B.
Manuʻa District
Manuʻa District is an administrative district of American Samoa encompassing the remote Manuʻa Islands in the eastern part of the territory.
-
C.
Kaliua District
Kaliua District is an administrative district located in western Tanzania, within the country’s Tabora Region.
-
D.
Petauke District
Petauke District is an administrative district in Zambia’s Eastern Province, known as an important agricultural area and a key stop along the route between Lusaka and the Malawi border.
-
E.
Naitasiri Province
Naitasiri Province is an inland province on the island of Viti Levu in Fiji, known for its rugged highlands, agriculture, and proximity to the capital city, Suva.
- 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_69c6882b3a108190b3a9eb343ae4162c |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6ae8dad608190b4708368a7af6e5d |
completed | March 27, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6e42945348190882e6ffd05977d36 |
completed | March 27, 2026, 8:10 p.m. |
| NEDg | Description generation | batch_69c6e5b236888190b108de51c730179a |
completed | March 27, 2026, 8:16 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c6e7cc21548190b302e2e31f9cadd0 |
completed | March 27, 2026, 8:25 p.m. |
Created at: March 27, 2026, 1:54 p.m.