Triple
T2784792
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Unilever |
E61784
|
entity |
| Predicate | foundedBy |
P104
|
FINISHED |
| Object | Margarine Unie |
E61784
|
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: Margarine Unie | Statement: [Unilever, foundedBy, Margarine Unie]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Margarine Unie Context triple: [Unilever, foundedBy, Margarine Unie]
-
A.
Danone
Danone is a multinational French food-products corporation best known for its dairy, plant-based, and bottled water brands.
-
B.
Unilever
chosen
Unilever is a multinational consumer goods company known for its wide range of food, personal care, and household products sold globally.
-
C.
Petit & Fritsen
Petit & Fritsen is a historic Dutch bell foundry renowned for casting church bells and carillons used in notable towers and monuments worldwide.
-
D.
Kraft
Kraft is a prominent American surname most widely associated with billionaire businessman and New England Patriots owner Robert Kraft.
-
E.
Nestlé
Nestlé is a Swiss multinational food and beverage conglomerate and one of the world’s largest consumer goods companies.
- 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_69ab4b7e43c48190997b8fc8fb1663ab |
completed | March 6, 2026, 9:47 p.m. |
| NER | Named-entity recognition | batch_69abdd9e11e48190af48f605062ea387 |
completed | March 7, 2026, 8:11 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afc0629e8c81909b55d9838e681ba2 |
completed | March 10, 2026, 6:55 a.m. |
Created at: March 6, 2026, 9:57 p.m.