Triple
T3010813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hertzogville |
E82212
|
entity |
| Predicate | provinceCapitalDistanceRelation |
P28400
|
FINISHED |
| Object | northwest of Bloemfontein |
—
|
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: northwest of Bloemfontein | Statement: [Hertzogville, provinceCapitalDistanceRelation, northwest of Bloemfontein]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: provinceCapitalDistanceRelation Context triple: [Hertzogville, provinceCapitalDistanceRelation, northwest of Bloemfontein]
-
A.
distanceFromCapital
Indicates the measured distance between a given location and the capital city of its corresponding region or country.
-
B.
countryCapitalDistrict
Indicates that a specified district serves as the capital district (administrative capital area) of a given country.
-
C.
countryCapitalNearby
Indicates that a country’s capital city is geographically close to a specified location or entity.
-
D.
stateCapitalProximity
chosen
Indicates the spatial closeness or distance between a state’s capital city and another specified location.
-
E.
regionCapital
Indicates that one entity is the capital city or administrative center of a specified region.
- 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_69ad8b1eb53481908c39bbcd1ec104b2 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a4e2c8c8190a8fed3604780826b |
completed | March 8, 2026, 3:48 p.m. |
| PD | Predicate disambiguation | batch_69ad96180eb08190a524c5f458d41382 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 3 p.m.