Triple
T20242230
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cēsis |
E498325
|
entity |
| Predicate | hasRoadConnectionTo |
P11435
|
FINISHED |
| Object | Sigulda |
—
|
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: Sigulda | Statement: [Cēsis, hasRoadConnectionTo, Sigulda]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sigulda Context triple: [Cēsis, hasRoadConnectionTo, Sigulda]
-
A.
Sigulda
chosen
Sigulda is a Latvian town in the scenic Gauja River valley, known for its medieval castles, dramatic landscapes, and status as a popular outdoor and winter sports destination.
-
B.
Laima
Laima is a major Baltic goddess associated with fate, luck, and childbirth in traditional Latvian and Lithuanian mythology.
-
C.
Égly
Égly is a small commune in the Essonne department of the Île-de-France region in northern France.
-
D.
Valka
Valka is a compassionate and fiercely independent dragon rider who serves as Hiccup’s long-lost mother and a key protector of dragons in the How to Train Your Dragon film series.
-
E.
Aldona
Aldona is a scenic riverside village in North Goa, India, known for its lush landscapes, historic churches, and traditional Goan charm.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69da6274c58c81909c646eabed6f4f30 |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e6716f9d248190a145f6883827ebbe |
completed | April 20, 2026, 6:33 p.m. |
Created at: April 11, 2026, 11:40 p.m.