Triple
T12838701
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sumy Oblast |
E306986
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object | Romny |
E544209
|
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: Romny | Statement: [Sumy Oblast, hasMajorCity, Romny]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Romny Context triple: [Sumy Oblast, hasMajorCity, Romny]
-
A.
Romny
chosen
Romny is a historic town in northeastern Ukraine known for its role as a regional trade and cultural center.
-
B.
Cambria Heights
Cambria Heights is a predominantly residential neighborhood in southeastern Queens, New York City, known for its suburban character and diverse community.
-
C.
Matraman
Matraman is a district in East Jakarta, Indonesia, known as one of the city's older urban residential and commercial areas.
-
D.
Tappan
The Tappan were a Lenape (Delaware) Native American group who inhabited parts of present-day New York and New Jersey during the early colonial period.
-
E.
Fresh Meadows
Fresh Meadows is a primarily residential neighborhood in the northeastern part of Queens, New York City, known for its garden apartment complexes and suburban-style layout.
- 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_69d7bdf52b94819096d6f0ba4ab50a98 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96ff11b4481909fb2f92c46186853 |
completed | April 10, 2026, 9:47 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6b8c962f08190af7dee663a1d2319 |
completed | May 3, 2026, 2:54 a.m. |
Created at: April 9, 2026, 5:35 p.m.