Triple
T4786682
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yerevan |
E106494
|
entity |
| Predicate | hasSisterCity |
P919
|
FINISHED |
| Object | Chișinău |
E134770
|
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: Chișinău | Statement: [Yerevan, hasSisterCity, Chișinău]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Chișinău Context triple: [Yerevan, hasSisterCity, Chișinău]
-
A.
Chișinău
chosen
Chișinău is the largest city and main political, economic, and cultural center of Moldova.
-
B.
Tiraspol
Tiraspol is the de facto capital and largest city of the unrecognized breakaway region of Transnistria in eastern Moldova.
-
C.
Iași
Iași is a major cultural, academic, and economic center in northeastern Romania, known for its historic universities, churches, and role as a former capital of the Principality of Moldavia.
-
D.
Beltsy, Moldova
Beltsy, Moldova is a major industrial and cultural city in northern Moldova, often considered the country’s second-largest urban center.
-
E.
Bucharest
Bucharest is the capital and largest city of Romania, known for its mix of historic architecture, wide boulevards, and its role as the country’s political, cultural, and economic center.
- 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_69bd43f4a9588190bf73e20bc27c03cc |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd65d8f9d881909c24340b8dc6a104 |
completed | March 20, 2026, 3:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43e01f6c81909ca0121c36d107e9 |
completed | March 21, 2026, 7:08 a.m. |
Created at: March 20, 2026, 1:22 p.m.