Triple
T38098849
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rokiškis |
E951319
|
entity |
| Predicate | hasManorPark |
P22590
|
FINISHED |
| Object | Rokiškis Manor Park |
E2255535
|
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: Rokiškis Manor Park | Statement: [Rokiškis, hasManorPark, Rokiškis Manor Park]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasManorPark Context triple: [Rokiškis, hasManorPark, Rokiškis Manor Park]
-
A.
hasThemePark
Indicates that one entity owns, contains, or is associated with a theme park as part of its properties or offerings.
-
B.
hasMotorParks
Indicates that an entity provides or contains designated areas or facilities for parking motor vehicles.
-
C.
hasParkAccess
Indicates that an entity is permitted to enter, use, or otherwise access a specified park or park area.
-
D.
hasThemeParkAreaIP
Indicates that a theme park area is based on, licensed from, or themed around a specific intellectual property (such as a franchise, brand, or media property).
-
E.
hasParks
chosen
Indicates that one entity possesses, contains, or is associated with one or more parks.
- F. None of above.
Provenance (4 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_69f76f04960c8190a83f14ae4c67f5bc |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_6a037df1223c8190a5d61e4f8e6fd613 |
completed | May 12, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a417b1fc6708190b22f0deb66bc51c3 |
completed | June 28, 2026, 7:50 p.m. |
| PD | Predicate disambiguation | batch_6a037a1ad6c48190bfe35d350c1b4751 |
completed | May 12, 2026, 7:06 p.m. |
Created at: May 3, 2026, 4:21 p.m.