Triple
T28652331
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Politics of Ceylon |
E725233
|
entity |
| Predicate | appliesToCurrentCountry |
P181121
|
FINISHED |
| Object | Sri Lanka |
—
|
NE NERFINISHED |
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: Sri Lanka | Statement: [Politics of Ceylon, appliesToCurrentCountry, Sri Lanka]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: appliesToCurrentCountry Context triple: [Politics of Ceylon, appliesToCurrentCountry, Sri Lanka]
-
A.
appliedToCurrentCountry
chosen
Indicates that something (such as a rule, setting, or operation) is applied specifically to the country that is currently in context.
-
B.
locatedInCurrentCountry
Indicates that an entity is situated within the geographic boundaries of the country in which it is presently found.
-
C.
correspondsToCountry
Indicates that one entity is associated with, matches, or represents a specific country.
-
D.
includesPresentCountry
Indicates that an entity (such as a region, organization, or grouping) currently contains or encompasses a specified country within its present composition or membership.
-
E.
appliesToPersonNationality
Indicates that something is relevant or applicable specifically to a person’s nationality.
- 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_69f01d84f5f0819087ab5e6143b14ed7 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69fd0b92f42881908cd77e3f058adcc2 |
completed | May 7, 2026, 10 p.m. |
| PD | Predicate disambiguation | batch_69fd0a3d68d4819094d92040f7c48d7c |
completed | May 7, 2026, 9:55 p.m. |
Created at: April 28, 2026, 4:52 a.m.