Triple
T226867
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | European Union |
E4332
|
entity |
| Predicate | countryCount |
P3809
|
FINISHED |
| Object | 27 member states |
—
|
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: 27 member states | Statement: [European Union, countryCount, 27 member states]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryCount Context triple: [European Union, countryCount, 27 member states]
-
A.
hasNumberOfCountries
chosen
Indicates the relationship that specifies how many countries are associated with or contained within a given entity.
-
B.
countryType
Indicates the classification or category of a country based on a specified typology (e.g., political, economic, or geographic type).
-
C.
countryDeJure
Indicates that one entity is the legally recognized (de jure) country having sovereignty or authority over another entity.
-
D.
countryLed
Indicates that one country serves as the leader, head, or primary directing authority over another country in a given context.
-
E.
countryWithOfficialStatus
Indicates that a country holds an official, legally recognized status in relation to the referenced entity.
- 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_69a257363ffc81909757bde7ab3404da |
completed | Feb. 28, 2026, 2:47 a.m. |
| NER | Named-entity recognition | batch_69a25d10ac248190a98dedabf5358668 |
completed | Feb. 28, 2026, 3:12 a.m. |
| PD | Predicate disambiguation | batch_69a25b5877588190af694d060377f027 |
completed | Feb. 28, 2026, 3:04 a.m. |
Created at: Feb. 28, 2026, 2:53 a.m.