Triple
T12179034
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brac |
E290167
|
entity |
| Predicate | hasHighestPoint |
P210
|
FINISHED |
| Object | Vidova Gora |
E473209
|
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: Vidova Gora | Statement: [Brac, hasHighestPoint, Vidova Gora]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vidova Gora Context triple: [Brac, hasHighestPoint, Vidova Gora]
-
A.
Vidova Gora
chosen
Vidova Gora is a prominent mountain peak on the Croatian island of Brač, known for its sweeping views over the Adriatic Sea and nearby islands.
-
B.
Labudovo Brdo
Labudovo Brdo is a residential neighborhood in the Čukarica municipality of Belgrade, Serbia.
-
C.
Sveta Gora Hill
Sveta Gora Hill is a prominent elevated area near Veliko Tarnovo, Bulgaria, known for its scenic views and historical and cultural significance.
-
D.
Czarna Góra
Czarna Góra is a village in southern Poland, known as a mountain resort area in the Tatra region.
-
E.
Polhov Gradec Hills
The Polhov Gradec Hills are a picturesque hilly region in central Slovenia known for their forested landscapes, traditional rural settlements, and popular hiking routes near Ljubljana.
- 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_69d6ab64de5881908d56eb7a75c6cc69 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d915fa6ff08190a1ddb3606c229cad |
completed | April 10, 2026, 3:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f64b85782481908cca14d8e8345411 |
completed | May 2, 2026, 7:07 p.m. |
Created at: April 8, 2026, 9:50 p.m.