Triple
T17240331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Horyn River |
E418475
|
entity |
| Predicate | majorCityOnRiver |
P316
|
FINISHED |
| Object | Netishyn |
E865628
|
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: Netishyn | Statement: [Horyn River, majorCityOnRiver, Netishyn]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Netishyn Context triple: [Horyn River, majorCityOnRiver, Netishyn]
-
A.
Netishyn
chosen
Netishyn is a small city in western Ukraine known primarily for hosting the Khmelnytskyi Nuclear Power Plant.
-
B.
Netolicky
Netolicky is the surname of Bob Netolicky, an American former professional basketball player known for his career in the American Basketball Association (ABA).
-
C.
Neteyam
Neteyam is a Na'vi warrior-in-training and the eldest son of Jake Sully and Neytiri in James Cameron's Avatar film series.
-
D.
Nete
The Nete is a river in Belgium that flows through the Flemish region and serves as one of the main tributaries forming the Rupel River.
-
E.
Nispert
Nispert is a village that forms one of the municipal sections of the town of Eupen in the German-speaking Community of Belgium.
- 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_69d886d8e96081909870bff6c3d0bf09 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e42e1f385c8190ae44e702923b6f66 |
completed | April 19, 2026, 1:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0170f1511c8190b70cb37e713a406a |
completed | May 11, 2026, 6:02 a.m. |
Created at: April 10, 2026, 5:39 a.m.