Triple
T27635898
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leffe |
E696466
|
entity |
| Predicate | introducedAsBrandByABInBev |
P5261
|
FINISHED |
| Object | 20th century |
—
|
LITERAL 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: 20th century | Statement: [Leffe, introducedAsBrandByABInBev, 20th century]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: introducedAsBrandByABInBev Context triple: [Leffe, introducedAsBrandByABInBev, 20th century]
-
A.
introducedAsBrandBy
chosen
Indicates that one entity was presented or launched to the public or a market as a brand by another entity.
-
B.
introducedAsBrandFor
Indicates that one entity was presented or launched to the public specifically as the brand representing another entity.
-
C.
isSoftDrinkBrand
Indicates that a given entity functions as a brand whose products are categorized as soft drinks.
-
D.
isColaBrandOf
Indicates that a given brand is a cola-type soft drink brand belonging to or produced by a specified company or entity.
-
E.
introducedUnderBrand
Indicates that one entity was launched, released, or brought to market using the branding or brand identity of another entity.
- F. None of above.
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_69ef5909f3848190805f35b76833e722 |
completed | April 27, 2026, 12:39 p.m. |
| NER | Named-entity recognition | batch_69f7308a096081909d66a56f3c926806 |
completed | May 3, 2026, 11:24 a.m. |
| PD | Predicate disambiguation | batch_69f72a00c5f081908b6539d15baf4e12 |
completed | May 3, 2026, 10:57 a.m. |
Created at: April 27, 2026, 2:23 p.m.