Triple
T38492304
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rand goldfields |
E918084
|
entity |
| Predicate | majorTownOrCity |
P76028
|
FINISHED |
| Object | Johannesburg |
—
|
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: Johannesburg | Statement: [Rand goldfields, majorTownOrCity, Johannesburg]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: majorTownOrCity Context triple: [Rand goldfields, majorTownOrCity, Johannesburg]
-
A.
majorTownInRegion
Indicates that a town is one of the principal or most significant towns within a specified region.
-
B.
majorUrbanCenterIn
Indicates that a city or metropolitan area functions as a primary or significant urban center within the specified region or administrative unit.
-
C.
majorIntermediateCity
Indicates that a city functions as a significant but not primary urban center within a region, typically serving as an important hub between major cities and smaller localities.
-
D.
cityOrTown
chosen
Indicates that the subject is classified as a city or a town.
-
E.
majorCityAlong
Indicates that a major city is located along the course or path of a specified geographic feature, such as a river, road, or route.
- 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_69f76e9894208190a129a553a60ca58c |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_6a00532815c881908f10d9594458b3d7 |
completed | May 10, 2026, 9:43 a.m. |
| PD | Predicate disambiguation | batch_6a0052b9f030819081b8105bdcaf6d8f |
completed | May 10, 2026, 9:41 a.m. |
Created at: May 3, 2026, 4:31 p.m.