Triple
T27492593
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pärnu Concert Hall |
E693929
|
entity |
| Predicate | locatedInResortCity |
P19586
|
FINISHED |
| Object | Pärnu |
—
|
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: Pärnu | Statement: [Pärnu Concert Hall, locatedInResortCity, Pärnu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locatedInResortCity Context triple: [Pärnu Concert Hall, locatedInResortCity, Pärnu]
-
A.
locatedInResortTown
chosen
Indicates that something is situated within the boundaries of a town that is primarily known as a resort or vacation destination.
-
B.
isResortCityOn
Indicates that a city, characterized as a resort destination, is located on or directly adjacent to a specified geographic feature (such as a coast, lake, or mountain range).
-
C.
isResortTown
Indicates that a town functions primarily as a resort destination, typically focused on tourism, leisure, and vacation activities.
-
D.
isWithinResort
Indicates that one place, object, or activity is located inside the boundaries of a specific resort.
-
E.
isResortOf
Indicates that a location or facility functions as a resort associated with, belonging to, or serving a particular entity (such as a city, region, or organization).
- 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_69ef5382b9648190be0b1ef2ad5d043c |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69fee691952c8190822da83e46311d1d |
completed | May 9, 2026, 7:47 a.m. |
| PD | Predicate disambiguation | batch_69fee62f285c8190a625562a9b80526e |
completed | May 9, 2026, 7:45 a.m. |
Created at: April 27, 2026, 1:06 p.m.