Triple
T35313496
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | ULTRA |
E1019840
|
entity |
| Predicate | countryOfPrimaryResponsibility |
P159374
|
FINISHED |
| Object | United Kingdom |
E732
|
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: United Kingdom | Statement: [ULTRA, countryOfPrimaryResponsibility, United Kingdom]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryOfPrimaryResponsibility Context triple: [ULTRA, countryOfPrimaryResponsibility, United Kingdom]
-
A.
countryResponsible
Indicates that a specific country bears responsibility for an action, event, obligation, or outcome related to another entity.
-
B.
primaryReferenceCountry
chosen
Indicates the main country that serves as the primary point of reference or association for the related entity.
-
C.
countryOfImplementation
Indicates the country where an action, project, policy, or measure is actually carried out or put into effect.
-
D.
primaryLocationCountry
Indicates the country that serves as the main or primary location associated with the subject.
-
E.
laterPrimaryCountry
Indicates that one country becomes the primary or dominant country in a given context at a later time than another.
- 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_69f76de9d45c81908a2ed0956b448b65 |
completed | May 3, 2026, 3:46 p.m. |
| NER | Named-entity recognition | batch_6a01bb06422c819095bb42f6f3a0e801 |
completed | May 11, 2026, 11:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a38369ab8f881908d46272214d26df3 |
completed | June 21, 2026, 7:08 p.m. |
| PD | Predicate disambiguation | batch_6a01b9991c348190ac49b65ea2fd86ed |
completed | May 11, 2026, 11:12 a.m. |
Created at: May 3, 2026, 4:03 p.m.