Triple
T20395273
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Norsk Hydro |
E500185
|
entity |
| Predicate | spunOff |
P1257
|
FINISHED |
| Object | Yara International |
—
|
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: Yara International | Statement: [Norsk Hydro, spunOff, Yara International]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yara International Context triple: [Norsk Hydro, spunOff, Yara International]
-
A.
Yara International
chosen
Yara International is a Norwegian chemical company and one of the world’s leading producers of mineral fertilizers and crop nutrition solutions.
-
B.
Orkla
Orkla is a leading Norwegian conglomerate primarily focused on branded consumer goods, with significant operations across the Nordic and Baltic regions and parts of Central Europe and India.
-
C.
Orkla
Orkla is a major river in Trøndelag county, Norway, known for its scenic valley and renowned salmon fishing.
-
D.
SEA S.p.A.
SEA S.p.A. is the company that manages and operates Milan’s main airports, including Malpensa and Linate, providing airport infrastructure and related services.
-
E.
Aurizon
Aurizon is a major Australian rail freight company that operates extensive cargo services across key national routes.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0b4a71ebc8190b153a36c738730f4 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e67912d7948190ac2fda8ce95e5c70 |
completed | April 20, 2026, 7:05 p.m. |
Created at: April 16, 2026, 11:28 a.m.