Triple
T11682848
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Podlaskie Voivodeship |
E277661
|
entity |
| Predicate | containsTown |
P847
|
FINISHED |
| Object | Hajnówka |
E407578
|
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: Hajnówka | Statement: [Podlaskie Voivodeship, containsTown, Hajnówka]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hajnówka Context triple: [Podlaskie Voivodeship, containsTown, Hajnówka]
-
A.
Hajnówka
chosen
Hajnówka is a town in northeastern Poland known as a gateway to the Białowieża Forest and a center of Belarusian minority culture.
-
B.
Bujaków
Bujaków is a district and former village that is now part of the town of Mikołów in southern Poland.
-
C.
Rakowice
Rakowice is a historic district in Kraków, Poland, known for its large military cemetery and proximity to the city center.
-
D.
Korczyna
Korczyna is a village in southeastern Poland, known as a local administrative and residential center within the Subcarpathian region.
-
E.
Radziejowa
Radziejowa is a prominent mountain peak in southern Poland, known for its forested slopes, scenic views, and status as the highest summit of the Beskid Sądecki range.
- 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_69d6aafd0a448190b44da30af8c6c519 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d8a462bb2881909238107d34c0a28d |
completed | April 10, 2026, 7:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff4c2818ec8190ae926a0ffdeb7bb7 |
completed | May 9, 2026, 3 p.m. |
Created at: April 8, 2026, 9:40 p.m.