Triple
T26070876
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thabazimbi |
E657540
|
entity |
| Predicate | hasMiningCompanyPresence |
P56901
|
FINISHED |
| Object | Kumba Iron Ore |
—
|
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: Kumba Iron Ore | Statement: [Thabazimbi, hasMiningCompanyPresence, Kumba Iron Ore]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasMiningCompanyPresence Context triple: [Thabazimbi, hasMiningCompanyPresence, Kumba Iron Ore]
-
A.
hasCoalMiningCompany
Indicates that an entity is associated with or owns a company whose primary business is coal mining.
-
B.
miningCompany
Indicates a relationship where an entity operates as a company engaged in the extraction of natural resources from the earth.
-
C.
hasMiningProject
Indicates that an entity is associated with, operates, or is responsible for a mining project.
-
D.
hasMiningDistrict
Indicates that an entity possesses, contains, or is associated with a designated mining district within its domain or jurisdiction.
-
E.
hasMiningArea
chosen
Indicates that an entity possesses, controls, or is associated with a designated area where mining activities take place.
- 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_69ee5bbe539081909efc7f9dd7c1b53c |
completed | April 26, 2026, 6:38 p.m. |
| NER | Named-entity recognition | batch_69f6562fd3488190be1acd8c526a28d2 |
completed | May 2, 2026, 7:53 p.m. |
| PD | Predicate disambiguation | batch_69f651a731508190bb0c8c2462eba224 |
completed | May 2, 2026, 7:33 p.m. |
Created at: April 26, 2026, 7:29 p.m.