Triple
T11848006
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Iscor |
E281830
|
entity |
| Predicate | wasMajorCompanyIn |
P22346
|
FINISHED |
| Object | South African steel sector |
—
|
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: South African steel sector | Statement: [Iscor, wasMajorCompanyIn, South African steel sector]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasMajorCompanyIn Context triple: [Iscor, wasMajorCompanyIn, South African steel sector]
-
A.
isMajorCompanyIn
chosen
Indicates that a company is a leading or dominant business entity within a specified country, region, or market.
-
B.
hasMajorOrganization
Indicates that an entity is associated with or primarily represented by a major organization.
-
C.
hasCompanyName
Indicates that an entity is associated with or identified by a specific company name.
-
D.
hasCompanyNamedAfter
Indicates that one entity has a company whose name is derived from or identical to the other entity.
-
E.
hasIndustrialCompany
Indicates that one entity possesses, controls, or is associated with an industrial company.
- 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_69d6ab287ba48190a5178779fd19b9b7 |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d8a65c72088190b8de9550c455b788 |
completed | April 10, 2026, 7:27 a.m. |
| PD | Predicate disambiguation | batch_69d8a254a57481908a1e6ad97919c416 |
completed | April 10, 2026, 7:10 a.m. |
Created at: April 8, 2026, 9:43 p.m.