Triple
T27019603
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Singha Durbar |
E680627
|
entity |
| Predicate | locatedInNationCapital |
P5025
|
FINISHED |
| Object | Kathmandu |
—
|
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: Kathmandu | Statement: [Singha Durbar, locatedInNationCapital, Kathmandu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInNationCapital Context triple: [Singha Durbar, locatedInNationCapital, Kathmandu]
-
A.
locatedInNationCapitalRegion
Indicates that an entity is situated within the capital region of a specific nation.
-
B.
locatedInCapital
chosen
Indicates that an entity is situated within the capital city of a specified region, country, or administrative area.
-
C.
locatedInCountryCapitalSystem
Indicates that an entity is situated in the capital city of a specified country within a country–capital relationship system.
-
D.
locatedInCapitalCityPort
Indicates that something is situated within the port area of a country's capital city.
-
E.
locatedInCountryCapitalOfProvince
Indicates that an entity is located in the country that contains the capital city of a specified province.
- F. None of above.
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_69eeeb5450988190bfc9a3c012ac463a |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69fe68a4b67881909ca1d9f276f922e0 |
completed | May 8, 2026, 10:50 p.m. |
| PD | Predicate disambiguation | batch_69fe680234c88190b01f953987b74972 |
completed | May 8, 2026, 10:47 p.m. |
Created at: April 27, 2026, 7:08 a.m.