Triple
T30509199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Severstal |
E776360
|
entity |
| Predicate | hasRawMaterialBase |
P56483
|
FINISHED |
| Object | iron ore deposits |
—
|
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: iron ore deposits | Statement: [Severstal, hasRawMaterialBase, iron ore deposits]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRawMaterialBase Context triple: [Severstal, hasRawMaterialBase, iron ore deposits]
-
A.
hasMaterialResource
Indicates that an entity possesses, controls, or has access to a tangible material resource.
-
B.
hasResourceBase
chosen
Indicates that one entity possesses, is founded on, or derives from another entity serving as its fundamental resource or base.
-
C.
hasSourceMaterial
Indicates that something is derived from, based on, or created using a particular source material.
-
D.
hasProductionBase
Indicates that one entity serves as the primary location or base where another entity’s production or manufacturing activities are carried out.
-
E.
hasMaterialType
Indicates that something is composed of, made from, or characterized by a specific type of material.
- 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_69f2249a155c8190b1d512106007e9bb |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f7886be6d8819095ec62e4f2cee858 |
completed | May 3, 2026, 5:39 p.m. |
| PD | Predicate disambiguation | batch_69f7841440f48190b4346c08855951d2 |
completed | May 3, 2026, 5:21 p.m. |
Created at: April 29, 2026, 8:16 p.m.