Triple
T7762836
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tongatapu |
E176067
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Kolovai
Kolovai is a village on the Tongan island of Tongatapu, known for its traditional culture and historic significance.
|
E687601
|
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: Kolovai | Statement: [Tongatapu, hasSettlement, Kolovai]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kolovai Context triple: [Tongatapu, hasSettlement, Kolovai]
-
A.
Khoni
Khoni is a small town in western Georgia’s Imereti region, known for its historical churches and surrounding natural landscapes.
-
B.
Vahcuengh
Vahcuengh is the native autonym and standardized written form of the Zhuang language, a Tai language spoken primarily in Guangxi, China.
-
C.
Kelmis
Kelmis is a municipality in eastern Belgium located in the country's German-speaking region, known for its historical zinc mining industry and borderland character near Germany and the Netherlands.
-
D.
Taghmon
Taghmon is a village in County Wexford, Ireland, known for its historic ecclesiastical roots and rural community character.
-
E.
Krakhuna
Krakhuna is a Georgian white grape variety from the Imereti region, known for producing aromatic, full-bodied wines with pronounced acidity.
- 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: Kolovai Triple: [Tongatapu, hasSettlement, Kolovai]
Generated description
Kolovai is a village on the Tongan island of Tongatapu, known for its traditional culture and historic significance.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Kolovai Target entity description: Kolovai is a village on the Tongan island of Tongatapu, known for its traditional culture and historic significance.
-
A.
Khoni
Khoni is a small town in western Georgia’s Imereti region, known for its historical churches and surrounding natural landscapes.
-
B.
Vahcuengh
Vahcuengh is the native autonym and standardized written form of the Zhuang language, a Tai language spoken primarily in Guangxi, China.
-
C.
Kelmis
Kelmis is a municipality in eastern Belgium located in the country's German-speaking region, known for its historical zinc mining industry and borderland character near Germany and the Netherlands.
-
D.
Taghmon
Taghmon is a village in County Wexford, Ireland, known for its historic ecclesiastical roots and rural community character.
-
E.
Krakhuna
Krakhuna is a Georgian white grape variety from the Imereti region, known for producing aromatic, full-bodied wines with pronounced acidity.
- 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_69c69962923c8190ac74d28b4f9fe0a0 |
completed | March 27, 2026, 2:51 p.m. |
| NER | Named-entity recognition | batch_69c704061d1881909b5b42bb93d2b8a7 |
completed | March 27, 2026, 10:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8c7da8b848190b378f694118dfa19 |
completed | March 29, 2026, 6:34 a.m. |
| NEDg | Description generation | batch_69c8c8d7a51481908fd537dbb57a6116 |
completed | March 29, 2026, 6:38 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8c98179908190a68b7f029fff8e3c |
completed | March 29, 2026, 6:41 a.m. |
Created at: March 27, 2026, 4:09 p.m.