Triple
T16318401
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lindt & Sprüngli |
E396229
|
entity |
| Predicate | hasSubsidiary |
P254
|
FINISHED |
| Object | Küfferle |
E1207019
|
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: Küfferle | Statement: [Lindt & Sprüngli, hasSubsidiary, Küfferle]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Küfferle Context triple: [Lindt & Sprüngli, hasSubsidiary, Küfferle]
-
A.
Küfferle
chosen
Küfferle is a confectionery brand known for its chocolate products and is owned by the Swiss chocolatier Lindt & Sprüngli.
-
B.
Falko
Falko is a given name and variant of "Falco," used in various European countries, particularly in German-speaking regions.
-
C.
Gessler
Gessler is a fictional character best known as the tyrannical Austrian bailiff and antagonist in the William Tell legend.
-
D.
Ottmar
Ottmar is a German former football player and highly successful manager best known for leading Borussia Dortmund and Bayern Munich to numerous domestic and European titles.
-
E.
Werneck
Werneck is a market town in the Schweinfurt district of northern Bavaria, Germany, known for its baroque palace and surrounding rural landscape.
- 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_69d87f255b788190a400eba031dd85d8 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e296b3e3e081908a996b3e57ca4e32 |
completed | April 17, 2026, 8:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a002da6e6e08190a20cc51699e12dbc |
completed | May 10, 2026, 7:03 a.m. |
Created at: April 10, 2026, 5:06 a.m.