Triple
T4166254
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Bottle Works |
E84453
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Bottle Works |
E84453
|
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: Bottle Works | Statement: [Bottle Works, name, Bottle Works]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bottle Works Context triple: [Bottle Works, name, Bottle Works]
-
A.
Bottle Works
chosen
Bottle Works is an interactive exhibit at the World of Coca-Cola that showcases the bottling process and production of Coca-Cola beverages.
-
B.
Shotz Brewery
Shotz Brewery is the fictional Milwaukee beer factory where the main characters work in the classic American sitcom "Laverne & Shirley."
-
C.
Litovel Brewery
Litovel Brewery is a Czech brewery renowned for its traditional lagers and other beers produced in the town of Litovel in the Olomouc Region.
-
D.
Moo Brew brewery
Moo Brew brewery is a Tasmanian craft brewery known for its contemporary beers and close connection to the Museum of Old and New Art (MONA).
-
E.
Christian Heurich Brewing Company
The Christian Heurich Brewing Company was a prominent historic brewery in Washington, D.C., once one of the largest and most successful breweries in the United States.
- 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_69aed932cab48190b80ffe35f7029ae1 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af02ac8e788190a8f3563a2903bbad |
completed | March 9, 2026, 5:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b57f478c948190a997e006015e588d |
completed | March 14, 2026, 3:31 p.m. |
Created at: March 9, 2026, 3:44 p.m.