Triple
T14495933
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mariinsky Concert Hall |
E359498
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Xavier Fabre |
—
|
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: Xavier Fabre | Statement: [Mariinsky Concert Hall, architect, Xavier Fabre]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xavier Fabre Context triple: [Mariinsky Concert Hall, architect, Xavier Fabre]
-
A.
Xavier Fabre
chosen
Xavier Fabre is a French architect known for designing prominent cultural venues, including the Mariinsky Concert Hall in Saint Petersburg.
-
B.
Xavier Rigault
Xavier Rigault is a film producer known for his work on the French drama "Delicacy."
-
C.
Gabriel Serville
Gabriel Serville is a French Guianese politician who has served as president of the Territorial Collectivity of French Guiana and is known for his advocacy on social and economic issues in the region.
-
D.
François-Xavier Fabre
François-Xavier Fabre was a French Neoclassical painter and art collector from Montpellier, known for his portraits and for bequeathing his collection that helped form the core of the Musée Fabre.
-
E.
Francis Pierlot
Francis Pierlot was an American character actor known for his supporting roles in early 20th-century stage and film productions.
- 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_69d8279740308190af9df93a3af8592e |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69de93109cb081909a6e846db23a4635 |
completed | April 14, 2026, 7:18 p.m. |
Created at: April 10, 2026, 1:21 a.m.