Triple
T17456798
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sežana |
E425050
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Komen |
—
|
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: Komen | Statement: [Sežana, nearbySettlement, Komen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Komen Context triple: [Sežana, nearbySettlement, Komen]
-
A.
Komen
Komen is the surname associated with Susan G. Komen, whose name is borne by a major U.S. breast cancer advocacy and research organization.
-
B.
Komen
chosen
Komen is a municipality in western Slovenia’s Littoral region, known for its karst landscape and proximity to the Italian border.
-
C.
Corme
Corme is a coastal village in Galicia, northwestern Spain, known for its fishing heritage and dramatic Atlantic scenery along the Costa da Morte.
-
D.
Koules
Koules is a Venetian-era coastal fortress in Heraklion, Crete, that historically protected the city’s harbor and now serves as a prominent cultural and tourist landmark.
-
E.
Kaoma
Kaoma was a French-Brazilian band best known for their 1989 worldwide hit dance single "Lambada."
- 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_69d889db0ba481908402409af3b37917 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e45142b08481908cdd290692d796c3 |
completed | April 19, 2026, 3:51 a.m. |
Created at: April 10, 2026, 5:47 a.m.