Triple
T2224206
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Frank Lloyd Wright |
E48611
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Taliesin
Taliesin is Frank Lloyd Wright’s famed Wisconsin estate and studio, celebrated as a landmark of organic architecture and a central site in his life and work.
|
E244778
|
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: Taliesin | Statement: [Frank Lloyd Wright, notableWork, Taliesin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Taliesin Context triple: [Frank Lloyd Wright, notableWork, Taliesin]
-
A.
Myrddin Wyllt
Myrddin Wyllt is a legendary mad prophet and wild man of the woods from early Welsh tradition, often seen as a historical and mythological precursor to the later figure of Merlin.
-
B.
Wilfred
Wilfred is a masculine given name of English origin, notably borne by the World War I poet Wilfred Owen.
-
C.
Sir Geraint
Sir Geraint is a knight of Arthurian legend, best known from medieval Welsh and English romances for his chivalric exploits and his marriage to Enid.
-
D.
Dafydd
Dafydd is the Welsh form of the given name David, commonly used in Wales.
-
E.
Sir Gaerfyrddin
Sir Gaerfyrddin is the Welsh-language name for Carmarthenshire, a historic county in southwest Wales.
- 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: Taliesin Triple: [Frank Lloyd Wright, notableWork, Taliesin]
Generated description
Taliesin is Frank Lloyd Wright’s famed Wisconsin estate and studio, celebrated as a landmark of organic architecture and a central site in his life and work.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Taliesin Target entity description: Taliesin is Frank Lloyd Wright’s famed Wisconsin estate and studio, celebrated as a landmark of organic architecture and a central site in his life and work.
-
A.
Myrddin Wyllt
Myrddin Wyllt is a legendary mad prophet and wild man of the woods from early Welsh tradition, often seen as a historical and mythological precursor to the later figure of Merlin.
-
B.
Wilfred
Wilfred is a masculine given name of English origin, notably borne by the World War I poet Wilfred Owen.
-
C.
Sir Geraint
Sir Geraint is a knight of Arthurian legend, best known from medieval Welsh and English romances for his chivalric exploits and his marriage to Enid.
-
D.
Dafydd
Dafydd is the Welsh form of the given name David, commonly used in Wales.
-
E.
Sir Gaerfyrddin
Sir Gaerfyrddin is the Welsh-language name for Carmarthenshire, a historic county in southwest Wales.
- 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_69a88aa51b388190949868ec9766e587 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc03ec3788190b5ae32201364f7ab |
completed | March 7, 2026, 6:05 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ae6562c9448190b53c068c900bf0bf |
completed | March 9, 2026, 6:14 a.m. |
| NEDg | Description generation | batch_69ae667ee2fc8190b9e96d8b10d90ab1 |
completed | March 9, 2026, 6:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ae66d8ba688190a2102c00fc6231c4 |
completed | March 9, 2026, 6:21 a.m. |
Created at: March 4, 2026, 7:47 p.m.