Triple
T19617883
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gambrinus Brewery |
E470914
|
entity |
| Predicate | usesIngredient |
P12771
|
FINISHED |
| Object | Saaz hops |
—
|
NE NERFINISHED |
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: Saaz hops | Statement: [Gambrinus Brewery, usesIngredient, Saaz hops]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saaz hops Context triple: [Gambrinus Brewery, usesIngredient, Saaz hops]
-
A.
Saaz
chosen
Saaz is the German name for the Czech town of Žatec, historically renowned as a major center of hop-growing and beer production.
-
B.
Humulus
Humulus is a small genus of flowering plants in the hemp family best known for the hop plant used in brewing beer.
-
C.
Holland Malt
Holland Malt is a Dutch malting company that produces malt for the brewing and food industries.
-
D.
Saazish
Saazish is a 1975 Indian Hindi-language thriller film featuring Persis Khambatta in a prominent role.
-
E.
Pils
Pils is a Czech-style pilsner beer crafted by Lagunitas Brewing Company, known for its crisp, hoppy character and easy drinkability.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e510fa248190b7afb274a1d4cf73 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e640e346548190b12e38d716bdfc4f |
completed | April 20, 2026, 3:06 p.m. |
Created at: April 10, 2026, 1:43 p.m.