Triple
T9274615
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern Estonia |
E222913
|
entity |
| Predicate | hasCity |
P316
|
FINISHED |
| Object | Elva |
E787926
|
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: Elva | Statement: [Southern Estonia, hasCity, Elva]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Elva Context triple: [Southern Estonia, hasCity, Elva]
-
A.
Elva
chosen
Elva is a small town in southern Estonia known for its forests, lakes, and role as a local recreational and tourism center.
-
B.
Venucia
Venucia is a Chinese automobile marque known for producing affordable passenger vehicles, originally established as a local brand under the Renault–Nissan–Mitsubishi Alliance.
-
C.
Rea
Rea is a given name and surname that serves as an alternative spelling of the name Rae.
-
D.
Reva
Reva is an alternative name for the Narmada River, one of central India’s major and holiest rivers.
-
E.
Dalva
Dalva is a surname most notably associated with American film editor Robert Dalva, recognized for his work on major Hollywood productions.
- 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_69ca841ffe208190aa7bcffbef2f8379 |
completed | March 30, 2026, 2:09 p.m. |
| NER | Named-entity recognition | batch_69cd078a045c8190b2c4d1ec64b932ad |
completed | April 1, 2026, 11:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0b1f57db881908a42ad5b042d0872 |
completed | April 4, 2026, 6:38 a.m. |
Created at: March 30, 2026, 7:33 p.m.