Triple
T22863102
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Waterford Wedgwood plc |
E566977
|
entity |
| Predicate | brand |
P1500
|
FINISHED |
| Object | Rosenthal |
—
|
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: Rosenthal | Statement: [Waterford Wedgwood plc, brand, Rosenthal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rosenthal Context triple: [Waterford Wedgwood plc, brand, Rosenthal]
-
A.
Rosenthal
Rosenthal is a surname of German and Jewish origin borne by numerous notable individuals across fields such as journalism, politics, and the arts.
-
B.
Rosenthal
chosen
Rosenthal is a locality in the Pankow borough of Berlin, Germany, known for its village-like character and green residential areas.
-
C.
Rosenhorn
Rosenhorn is a notable subsidiary peak in the Bernese Alps of Switzerland, forming part of the Wetterhorn massif.
-
D.
Rosenstein
Rosenstein is a surname most notably associated with Justin Rosenstein, the American software programmer and co-founder of Asana.
-
E.
Ralbitz-Rosenthal
Ralbitz-Rosenthal is a small municipality in Saxony, Germany, known for its strong Sorbian cultural heritage and rural character.
- 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_69e24589083081908d5694c4fdc80086 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17efdc3b08190be03d856aa86b277 |
completed | April 29, 2026, 3:46 a.m. |
Created at: April 17, 2026, 3:38 p.m.