Triple
T18426242
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tara River Canyon |
E450145
|
entity |
| Predicate | nearestNationalParkCenter |
P81346
|
FINISHED |
| Object | Žabljak visitor facilities |
—
|
LITERAL 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: Žabljak visitor facilities | Statement: [Tara River Canyon, nearestNationalParkCenter, Žabljak visitor facilities]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: nearestNationalParkCenter Context triple: [Tara River Canyon, nearestNationalParkCenter, Žabljak visitor facilities]
-
A.
nearestNationalParkHeadquarters
chosen
Indicates that one location is the closest national park headquarters to another specified place.
-
B.
nearestNationalParkEntrance
Indicates the relationship where a given location is associated with the closest entrance point of a national park.
-
C.
hasNearbyStatePark
Indicates that a location is situated close to at least one designated state park.
-
D.
nearbyCountryPark
Indicates that a country park is located close to or within a short distance of a given reference place or area.
-
E.
locatedNearNationalPark
Indicates that one place or entity is situated in close proximity to a national park.
- 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_69d8d381d6388190a9e94e9c658174e4 |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e51b12606081908ea320fd8d5554c6 |
completed | April 19, 2026, 6:12 p.m. |
| PD | Predicate disambiguation | batch_69e469bf7f74819096a01173493412c2 |
completed | April 19, 2026, 5:35 a.m. |
Created at: April 10, 2026, 11:22 a.m.