Triple
T23413342
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ulpiana |
E560138
|
entity |
| Predicate | locatedNear |
P294
|
FINISHED |
| Object | Graçanica |
—
|
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: Graçanica | Statement: [Ulpiana, locatedNear, Graçanica]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Graçanica Context triple: [Ulpiana, locatedNear, Graçanica]
-
A.
Stari Ras
Stari Ras is an important medieval archaeological site and former capital of the early Serbian state, recognized today as a UNESCO World Heritage Site.
-
B.
Brežđe
Brežđe is a small village in Serbia known primarily as the birthplace of politician Ivan Stambolić.
-
C.
Gračanica
chosen
Gračanica is a town in central Kosovo known for its significant Serbian cultural and religious heritage, including the medieval Gračanica Monastery.
-
D.
Stari Grad
Stari Grad is the historic central municipality of Belgrade, known for its old town architecture, cultural landmarks, and key administrative and commercial areas.
-
E.
Stari Grad
Stari Grad is one of the oldest towns in Croatia, a historic harbor settlement on the island of Hvar known for its ancient Greek-era layout and UNESCO-listed surrounding plain.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a513502881909f33a43bfd5e63a7 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:39 p.m.