Triple
T3363451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Viti Levu |
E70777
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object | Nadi |
E347659
|
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: Nadi | Statement: [Viti Levu, contains, Nadi]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nadi Context triple: [Viti Levu, contains, Nadi]
-
A.
Nadi
chosen
Nadi is a major town on the western side of Fiji’s main island, known as a key tourism and transport hub for the country.
-
B.
Varuna River
The Varuna River is a minor but historically significant river in northern India that flows near Varanasi, contributing to the city’s name and sacred geography.
-
C.
Padma River
The Padma River is a major distributary of the Ganges in Bangladesh, known for its vast width, powerful currents, and crucial role in the country’s agriculture, fisheries, and transportation.
-
D.
Marico River
The Marico River is a significant watercourse in southern Africa that forms part of the upper reaches of the Limpopo River system.
-
E.
Hathmati River
The Hathmati River is a tributary river in the Indian state of Gujarat that feeds into the larger Sabarmati River system.
- 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_69b3545ea1b08190ad84b7e5f70b4d2e |
completed | March 13, 2026, 12:03 a.m. |
Created at: March 8, 2026, 3:13 p.m.