Triple
T19617874
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gambrinus Brewery |
E470914
|
entity |
| Predicate | hasProduct |
P3585
|
FINISHED |
| Object |
Gambrinus 12°
Gambrinus 12° is a popular Czech pale lager known for its balanced taste and higher original gravity, produced by the Gambrinus Brewery.
|
E1387893
|
NE FINISHED |
How this triple was built (4 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: Gambrinus 12° | Statement: [Gambrinus Brewery, hasProduct, Gambrinus 12°]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Gambrinus 12° Context triple: [Gambrinus Brewery, hasProduct, Gambrinus 12°]
-
A.
Gambrinus 10°
Gambrinus 10° is a popular Czech pale lager known for its light body, lower alcohol content, and easy drinkability.
-
B.
Gambrinus Unpasteurized
Gambrinus Unpasteurized is a Czech beer known for its fresh, full flavor preserved by skipping the pasteurization process.
-
C.
Kronenbourg 1664
Kronenbourg 1664 is a popular French pale lager beer known for its distinctive hop character and wide international distribution.
-
D.
Martell
Martell is a historic French cognac house renowned as one of the oldest and most prestigious producers in the Cognac region.
-
E.
Martell
Martell is a prominent noble house from Dorne in George R. R. Martin’s A Song of Ice and Fire series, known for its principality, distinct customs, and resistance to conquest.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Gambrinus 12° Triple: [Gambrinus Brewery, hasProduct, Gambrinus 12°]
Generated description
Gambrinus 12° is a popular Czech pale lager known for its balanced taste and higher original gravity, produced by the Gambrinus Brewery.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Gambrinus 12° Target entity description: Gambrinus 12° is a popular Czech pale lager known for its balanced taste and higher original gravity, produced by the Gambrinus Brewery.
-
A.
Gambrinus 10°
Gambrinus 10° is a popular Czech pale lager known for its light body, lower alcohol content, and easy drinkability.
-
B.
Gambrinus Unpasteurized
Gambrinus Unpasteurized is a Czech beer known for its fresh, full flavor preserved by skipping the pasteurization process.
-
C.
Kronenbourg 1664
Kronenbourg 1664 is a popular French pale lager beer known for its distinctive hop character and wide international distribution.
-
D.
Martell
Martell is a historic French cognac house renowned as one of the oldest and most prestigious producers in the Cognac region.
-
E.
Martell
Martell is a prominent noble house from Dorne in George R. R. Martin’s A Song of Ice and Fire series, known for its principality, distinct customs, and resistance to conquest.
- F. None of above. chosen
Provenance (5 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. |
| NED1 | Entity disambiguation (via context triple) | batch_6a077edc7028819097379146c15d9e64 |
completed | May 15, 2026, 8:15 p.m. |
| NEDg | Description generation | batch_6a077f87d96c8190a8d9ee82e84be1f2 |
completed | May 15, 2026, 8:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07816f54408190b6458ed0d17f9b60 |
completed | May 15, 2026, 8:26 p.m. |
Created at: April 10, 2026, 1:43 p.m.