Triple
T14356191
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hella Jongerius |
E355975
|
entity |
| Predicate | hasWorkedFor |
P11675
|
FINISHED |
| Object | IKEA |
E189093
|
NE 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: IKEA | Statement: [Hella Jongerius, hasWorkedFor, IKEA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IKEA Context triple: [Hella Jongerius, hasWorkedFor, IKEA]
-
A.
IKEA
chosen
IKEA is a multinational Swedish-founded retailer known for its affordable, flat-pack furniture, home goods, and large warehouse-style stores worldwide.
-
B.
Inter IKEA Systems B.V.
Inter IKEA Systems B.V. is the Dutch-based company that owns and manages the IKEA concept, brand, and franchising system worldwide.
-
C.
Iittala
Iittala is a Finnish design brand renowned for its high-quality glassware and timeless Scandinavian tableware and home objects.
-
D.
Crate & Barrel
Crate & Barrel is an American retail chain specializing in contemporary furniture, housewares, and home décor.
-
E.
Electrolux
Electrolux is a Swedish multinational home appliance manufacturer known for producing a wide range of kitchen and cleaning products for both consumers and professionals.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69d82790a7e08190877e2d349b2e8d8e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de8f519bf881908615f4d47e0f77aa |
completed | April 14, 2026, 7:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fd4c473fa48190866ab946971e971c |
completed | May 8, 2026, 2:36 a.m. |
Created at: April 10, 2026, 1:15 a.m.