Triple
T23514458
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mangareva |
E574317
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object | Rikitea |
—
|
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: Rikitea | Statement: [Mangareva, hasSettlement, Rikitea]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rikitea Context triple: [Mangareva, hasSettlement, Rikitea]
-
A.
Rikitea
chosen
Rikitea is the principal village and administrative hub of the Gambier Islands in French Polynesia, known for its lagoon setting and pearl-farming activities.
-
B.
Reihōkan
Reihōkan is the treasure hall of Daigo-ji Temple in Kyoto, housing an important collection of Buddhist art and cultural artifacts.
-
C.
Risshū
Risshū is a Japanese Buddhist monastic order founded by the Chinese monk Ganjin that emphasizes strict adherence to the Vinaya (monastic precepts).
-
D.
Daijō
Daijō is a Japanese term historically associated with imperial titles and court ranks, particularly in reference to retired emperors.
-
E.
Kiyosu
Kiyosu is a city in central Japan known historically for Kiyosu Castle and its role as a political center during the Sengoku period.
- 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_69e245bb3dcc8190ba9a2b35972b58d0 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1aa80d9048190ab735dddd301feb4 |
completed | April 29, 2026, 6:51 a.m. |
Created at: April 17, 2026, 6:08 p.m.