Triple
T30424144
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Embassy of Costa Rica in Moscow |
E773976
|
entity |
| Predicate | hostCountryCapitalOf |
P170456
|
FINISHED |
| Object | Russian Federation |
E10011
|
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: Russian Federation | Statement: [Embassy of Costa Rica in Moscow, hostCountryCapitalOf, Russian Federation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostCountryCapitalOf Context triple: [Embassy of Costa Rica in Moscow, hostCountryCapitalOf, Russian Federation]
-
A.
hostCountryCapitalCity
Indicates that a given city serves as the capital of a specified host country.
-
B.
homeCountryCapital
Indicates that a given city is the capital of a specified country that serves as an entity’s home or origin.
-
C.
hostsNationalCapitalOf
Indicates that a location serves as the site where the national capital city of a country is situated.
-
D.
hostsCapitalOf
Indicates that one location serves as the capital city of another administrative or political entity.
-
E.
associatedCountryCapital
Indicates that a country is related to, or paired with, its capital city.
- F. None of above. chosen
Provenance (5 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_69f22491ba248190b9a4776ca8e42d02 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f69063edbc81909e7735954aabee0b |
completed | May 3, 2026, 12:01 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a28e4420b248190a9c12ff59d24ab9d |
completed | June 10, 2026, 4:12 a.m. |
| PD | Predicate disambiguation | batch_69f68b7b03488190b1db5fde4c7dd6e5 |
completed | May 2, 2026, 11:40 p.m. |
| PDg | Predicate description generation | batch_69f68f6584a88190a8c4d95c0c84bee9 |
completed | May 2, 2026, 11:57 p.m. |
Created at: April 29, 2026, 8:06 p.m.