Triple
T1126544
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bloemfontein |
E24732
|
entity |
| Predicate | countryCapitalRole |
P25262
|
FINISHED |
| Object | judicial branch |
—
|
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: judicial branch | Statement: [Bloemfontein, countryCapitalRole, judicial branch]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: countryCapitalRole Context triple: [Bloemfontein, countryCapitalRole, judicial branch]
-
A.
regionCapital
Indicates that one entity is the capital city or administrative center of a specified region.
-
B.
countryCapitalOf
Indicates that a country serves as the capital location for a specified political or geographic entity.
-
C.
countryCapitalLocatedOn
Indicates that the capital city of a country is situated on or directly adjacent to a specified geographic feature (such as a river, coast, or lake).
-
D.
countryCapitalLegislatureRelation
Indicates that a specific legislature is located in, or officially associated with, the capital city of a given country.
-
E.
homeCountryCapital
Indicates that a given city is the capital of a specified country that serves as an entity’s home or origin.
- F. None of above. chosen
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_69a4940712c88190aa244f3fc6070a65 |
completed | March 1, 2026, 7:31 p.m. |
| NER | Named-entity recognition | batch_69a4bc4bc21881909dcfe628f59f3e8c |
completed | March 1, 2026, 10:23 p.m. |
| PD | Predicate disambiguation | batch_69a4bb4749ac8190b0fbddac2e9b2586 |
completed | March 1, 2026, 10:18 p.m. |
| PDg | Predicate description generation | batch_69a4bc47fce48190825d3a877251f789 |
completed | March 1, 2026, 10:23 p.m. |
Created at: March 1, 2026, 7:44 p.m.