Triple
T15472033
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Maison de la Radio |
E376684
|
entity |
| Predicate | architect |
P184
|
FINISHED |
| Object | Henry Bernard |
E153195
|
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: Henry Bernard | Statement: [Maison de la Radio, architect, Henry Bernard]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Bernard Context triple: [Maison de la Radio, architect, Henry Bernard]
-
A.
Henry Bernard
chosen
Henry Bernard was a prominent 20th-century French architect known for his modernist public buildings and influential role in postwar urban planning.
-
B.
Henry Yorke
Henry Yorke is a British novelist better known by his pen name Henry Green, acclaimed for his innovative modernist fiction in the mid-20th century.
-
C.
Bertram Raphael
Bertram Raphael is an American computer scientist and artificial intelligence pioneer known for his work in automated reasoning and early AI research at institutions such as SRI International.
-
D.
Bernard David Jones
Bernard David Jones is an American actor best known for his comedic television roles, including a prominent part in the sitcom "The Mayor."
-
E.
Henry Gayden
Henry Gayden is an American screenwriter best known for writing the superhero film "Shazam!" and its sequel in the DC Extended Universe.
- 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_69d85cd21dcc81908646251b1c26ea00 |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e03f6c57308190b4cfe661c26addd4 |
completed | April 16, 2026, 1:46 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff2d0543f881909dfbbc77f2a96a1a |
completed | May 9, 2026, 12:48 p.m. |
Created at: April 10, 2026, 3:33 a.m.