Triple
T15222573
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | YYA Treaty |
E363797
|
entity |
| Predicate | shortNameInFinnish |
P85296
|
FINISHED |
| Object | Ystävyys-, yhteistyö- ja avunantosopimus |
—
|
LITERAL 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: Ystävyys-, yhteistyö- ja avunantosopimus | Statement: [YYA Treaty, shortNameInFinnish, Ystävyys-, yhteistyö- ja avunantosopimus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: shortNameInFinnish Context triple: [YYA Treaty, shortNameInFinnish, Ystävyys-, yhteistyö- ja avunantosopimus]
-
A.
usesNameInFinnish
Indicates that an entity is referred to or identified by a specific name when using the Finnish language.
-
B.
hasFinnishAbbreviation
Indicates that one entity is the standard Finnish-language abbreviation or shortened form of another entity.
-
C.
hasOfficialNameInFinnish
chosen
Indicates that an entity has a specific official name expressed in the Finnish language.
-
D.
shortNameInJapanese
Indicates that an entity has a specific abbreviated or shorter form of its name expressed in the Japanese language.
-
E.
shortNameInThai
Indicates that an entity has a short or abbreviated name expressed in the Thai language.
- F. None of above.
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_69d85a0ce24c81909c4d3b6475548c95 |
completed | April 10, 2026, 2:01 a.m. |
| NER | Named-entity recognition | batch_69e00788b04881909dad9b346ce3b4a9 |
completed | April 15, 2026, 9:47 p.m. |
| PD | Predicate disambiguation | batch_69deca8479188190b2e5d3bc708d7d07 |
completed | April 14, 2026, 11:15 p.m. |
Created at: April 10, 2026, 3:12 a.m.