Triple
T11419119
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | JWT |
E270570
|
entity |
| Predicate | notableClient |
P7186
|
FINISHED |
| Object | Unilever |
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: Unilever | Statement: [JWT, notableClient, Unilever]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Unilever Context triple: [JWT, notableClient, Unilever]
-
A.
Unilever
chosen
Unilever is a multinational consumer goods company known for its wide range of food, personal care, and household products sold globally.
-
B.
Procter & Gamble
Procter & Gamble is a multinational consumer goods corporation known for a wide range of household, personal care, and hygiene brands sold globally.
-
C.
Reckitt Benckiser
Reckitt Benckiser is a British multinational consumer goods company best known for its health, hygiene, and home products such as Dettol, Lysol, and Durex.
-
D.
Henkel
Henkel is a German multinational chemical and consumer goods company best known for its brands in laundry, home care, and adhesives.
-
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_69d6aaddeaa8819088b30ef7b50598c9 |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d801b20ce08190befc98379b879985 |
completed | April 9, 2026, 7:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e5b88f80d88190b91b63d0b7457c25 |
completed | April 20, 2026, 5:24 a.m. |
Created at: April 8, 2026, 9:34 p.m.