Triple
T11999977
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mogilev Region |
E285632
|
entity |
| Predicate | containsCity |
P294
|
FINISHED |
| Object | Horki |
E471490
|
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: Horki | Statement: [Mogilev Region, containsCity, Horki]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Horki Context triple: [Mogilev Region, containsCity, Horki]
-
A.
Horki
chosen
Horki is a town in eastern Belarus known for its agricultural academy and regional administrative significance.
-
B.
Horezu
Horezu is a small Romanian town renowned for its traditional pottery and UNESCO-recognized ceramic craftsmanship.
-
C.
Uherka
Uherka is a river in eastern Poland that serves as a tributary of the Western Bug, flowing through the Lublin region.
-
D.
Krakhuna
Krakhuna is a Georgian white grape variety from the Imereti region, known for producing aromatic, full-bodied wines with pronounced acidity.
-
E.
Gundrak
Gundrak is a troll-themed dungeon instance in World of Warcraft set in the Zul'Drak region of Northrend, featuring the Drakkari empire and their loa gods.
- 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903c26d7881909b67a31d04882eb5 |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f472917ed08190a872d9e5663d5ed5 |
completed | May 1, 2026, 9:29 a.m. |
Created at: April 8, 2026, 9:46 p.m.