Triple
T13386812
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gulf of Bone |
E319464
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Bone Regency |
E121181
|
NE FINISHED |
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: Bone Regency | Statement: [Gulf of Bone, near, Bone Regency]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bone Regency Context triple: [Gulf of Bone, near, Bone Regency]
-
A.
Bone Regency
chosen
Bone Regency is an administrative region in South Sulawesi, Indonesia, historically significant as a core homeland of the Bugis people.
-
B.
Regals
Regals is the team name and mascot identity for the women's athletic programs at California Lutheran University.
-
C.
Sikka Regency
Sikka Regency is an administrative region on the island of Flores in East Nusa Tenggara, Indonesia, known for its coastal landscapes and traditional Sikka culture.
-
D.
Crown
Crown is a major American publishing imprint of Penguin Random House known for releasing high-profile nonfiction and bestselling works by prominent public figures.
-
E.
Crown
Crown is a prominent American business family name associated with influential industrialist and investor Lester Crown.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d806b886bc8190b676e7768b8e01c5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dadce96d1881909957fdd068a7f55d |
completed | April 11, 2026, 11:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f7268f9a908190843481dd313f5a11 |
completed | May 3, 2026, 10:42 a.m. |
Created at: April 9, 2026, 9:34 p.m.