Triple
T37947613
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wysokie Mazowieckie |
E946648
|
entity |
| Predicate | hasNearbyLargerCity |
P112043
|
FINISHED |
| Object | Białystok |
—
|
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: Białystok | Statement: [Wysokie Mazowieckie, hasNearbyLargerCity, Białystok]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNearbyLargerCity Context triple: [Wysokie Mazowieckie, hasNearbyLargerCity, Białystok]
-
A.
largestNearbyCity
Indicates that one city is the largest (by population, area, or another defined metric) among the cities located within a specified nearby region of another place or city.
-
B.
nearestLargeUrbanArea
chosen
Indicates that one entity is the closest major city or large urban center to the other entity.
-
C.
hasNearbyMajorCityCountry
Indicates that an entity has a nearby major city located in the specified country.
-
D.
adjacentMajorCity
Indicates that one major city is geographically next to or directly bordering another major city.
-
E.
nearestSmallCity
Indicates that one city is the closest small-sized city in distance or proximity to another specified location or entity.
- F. None of above.
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_69f76ef64cf08190ad3e1114b62aac67 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a00b03a50a88190bfb95cdcfc6142a2 |
completed | May 10, 2026, 4:20 p.m. |
| PD | Predicate disambiguation | batch_6a00afe55f248190b2cb4c7e62cc3ffc |
completed | May 10, 2026, 4:18 p.m. |
Created at: May 3, 2026, 4:20 p.m.