Triple
T38509423
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rumia |
E921860
|
entity |
| Predicate | twinTownIn |
P92044
|
FINISHED |
| Object | Estonia |
E22105
|
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: Estonia | Statement: [Rumia, twinTownIn, Estonia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: twinTownIn Context triple: [Rumia, twinTownIn, Estonia]
-
A.
twinTownInCountry
chosen
Indicates that a town’s twin or sister city relationship is specifically with a town located in the given country.
-
B.
hasTwinTown
Indicates that two towns or cities are officially paired in a twinning relationship, typically for cultural, social, or economic exchange.
-
C.
twinCity
Indicates that two cities are officially recognized as twin (or sister) cities, typically signifying a formal partnership for cultural, economic, or social exchange.
-
D.
fromTown
Indicates that one entity originates from, or is associated as being from, a particular town represented by the other entity.
-
E.
hasNearbyTown
Indicates that one location has a town situated close to it in geographic proximity.
- F. None of above.
Provenance (4 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_69f76ea3c5448190aa7002fc1ba3f874 |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fcd313e61c8190b174b331365b803f |
completed | May 7, 2026, 5:59 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a41e015139c8190983b97753e3045f1 |
completed | June 29, 2026, 3:01 a.m. |
| PD | Predicate disambiguation | batch_69fcd1f6b2e08190bf0300ae7c9ae67a |
completed | May 7, 2026, 5:55 p.m. |
Created at: May 3, 2026, 4:32 p.m.