Triple
T21328119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Makira Island |
E525816
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Kirakira |
—
|
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: Kirakira | Statement: [Makira Island, hasCity, Kirakira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Kirakira Context triple: [Makira Island, hasCity, Kirakira]
-
A.
Kirakira
chosen
Kirakira is a small coastal town in the Solomon Islands that serves as the administrative and commercial center of Makira-Ulawa Province.
-
B.
Ikara
Ikara is the traditional Aboriginal name for Wilpena Pound, a spectacular natural amphitheatre of mountains in South Australia's Flinders Ranges.
-
C.
Ikire
Ikire is a prominent town in southwestern Nigeria known for its location along major transport routes and its distinctive local delicacies, particularly “dodo Ikire.”
-
D.
Kirike
Kirike is the self-designated name (autonym) used by the Okrika Ijaw people for themselves and their language in the Niger Delta region of Nigeria.
-
E.
Kitakata
Kitakata is a city in northern Japan renowned for its traditional kura storehouses and distinctive Kitakata-style ramen.
- 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_69e0b51b90788190a4dd823d962626da |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69e7ab4e88848190b6efe85a4c8cd85a |
completed | April 21, 2026, 4:52 p.m. |
Created at: April 16, 2026, 4:41 p.m.