Triple
T9276059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Toomas |
E222950
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Toomás |
E222950
|
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: Toomás | Statement: [Toomas, hasVariant, Toomás]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Toomás Context triple: [Toomas, hasVariant, Toomás]
-
A.
Toomas
chosen
Toomas is a masculine given name commonly used in Estonia and other Baltic and Nordic countries, equivalent to the English name Thomas.
-
B.
Tuuli Narkle
Tuuli Narkle is an Australian actress known for her role in the television crime drama series NCIS: Sydney.
-
C.
Kustavi
Kustavi is a small coastal municipality and popular summer resort area in southwestern Finland, known for its archipelago scenery and cottage culture.
-
D.
Edgar Savisaar
Edgar Savisaar is an Estonian politician and founding figure of the post-Soviet Estonian state, known for leading the Popular Front of Estonia and serving in several top government roles.
-
E.
Väinö
Väinö is a Finnish masculine given name historically borne by several notable figures in politics, arts, and sports in Finland.
- 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_69cd07c71b5c8190b5b7b5ab4224e9d3 |
completed | April 1, 2026, 11:55 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d09c3dd140819099fc0e95c4d48ba9 |
completed | April 4, 2026, 5:06 a.m. |
Created at: March 30, 2026, 7:34 p.m.