Triple
T15428473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madhesh Province |
E369573
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Janakpur |
E254454
|
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: Janakpur | Statement: [Madhesh Province, containsCity, Janakpur]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Janakpur Context triple: [Madhesh Province, containsCity, Janakpur]
-
A.
Janakpur
chosen
Janakpur is a historic cultural and religious center in the Mithila region, renowned as a major pilgrimage site associated with the Hindu epic Ramayana.
-
B.
Birgunj
Birgunj is a major commercial and industrial city in southern Nepal, serving as a key trade gateway with India.
-
C.
Nepalgunj
Nepalgunj is a major city in southwestern Nepal known as a commercial and transportation hub near the Indian border.
-
D.
Patan
Patan is an ancient city in the Kathmandu Valley of Nepal, renowned for its rich Newar culture, traditional arts, and historic Durbar Square filled with temples and palaces.
-
E.
Tikapur
Tikapur is a town in far‑western Nepal known for its planned urban layout and the large riverside Tikapur Park along the Karnali River.
- 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_69d85a1849f48190bf898068b2806fae |
completed | April 10, 2026, 2:02 a.m. |
| NER | Named-entity recognition | batch_69e03ec31f4881908b26ff7c381d7bc9 |
completed | April 16, 2026, 1:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2cf5d788819086a94af42c2ec21a |
completed | May 9, 2026, 12:47 p.m. |
Created at: April 10, 2026, 3:20 a.m.