Triple
T21375782
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Třebíč |
E527197
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Humenné |
—
|
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: Humenné | Statement: [Třebíč, hasTwinTown, Humenné]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Humenné Context triple: [Třebíč, hasTwinTown, Humenné]
-
A.
Humenné
chosen
Humenné is a town in eastern Slovakia known as a regional industrial hub with a significant chemical and machinery sector.
-
B.
Husinec
Husinec is a small Czech town best known as the birthplace of the religious reformer Jan Hus.
-
C.
Hartmanice
Hartmanice is a small town in the Plzeň Region of the Czech Republic, known for its location in the Šumava (Bohemian Forest) area.
-
D.
Huchnom
Huchnom refers to a subgroup of the Yuki people, an Indigenous group native to what is now Northern California.
-
E.
Hrebienok
Hrebienok is a popular mountain tourist resort and trailhead in the High Tatras of Slovakia, known for its easy cable car access and hiking routes.
- 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_69e0b51e80808190ba5cb05667af02a9 |
completed | April 16, 2026, 10:08 a.m. |
| NER | Named-entity recognition | batch_69ee5bb031988190ae587730a2131a50 |
completed | April 26, 2026, 6:38 p.m. |
Created at: April 16, 2026, 5:11 p.m.