Triple
T3363452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viti Levu |
E70777
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Lautoka |
E347662
|
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: Lautoka | Statement: [Viti Levu, contains, Lautoka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lautoka Context triple: [Viti Levu, contains, Lautoka]
-
A.
Lautoka
chosen
Lautoka is Fiji's second-largest city, located on the western coast of Viti Levu and known as a major port and center of the country's sugar industry.
-
B.
Laja
Laja is a small Chilean city in the Biobío Region, known for its riverside setting and proximity to the Biobío River.
-
C.
Lisnaskea
Lisnaskea is a small market town in County Fermanagh, Northern Ireland, known for serving as a local commercial and community hub for the surrounding rural area.
-
D.
Laus
Laus was an ancient Greek colony in southern Italy, founded by settlers from the wealthy city of Sybaris.
-
E.
Taalunie
Taalunie is an international institution that coordinates and promotes the Dutch language and literature across Dutch-speaking regions.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb26a5a508190948932769de0dbb3 |
completed | March 8, 2026, 5:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b32549eb9c81908c3a525da9eab0aa |
completed | March 12, 2026, 8:42 p.m. |
Created at: March 8, 2026, 3:13 p.m.