Triple
T29024329
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Château d’Hérouville |
E737546
|
entity |
| Predicate | foundedAsStudioBy |
P11844
|
FINISHED |
| Object | Michel Magne |
—
|
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: Michel Magne | Statement: [Château d’Hérouville, foundedAsStudioBy, Michel Magne]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundedAsStudioBy Context triple: [Château d’Hérouville, foundedAsStudioBy, Michel Magne]
-
A.
foundedAsStudioIn
Indicates that an entity was originally established or created in the form of a studio at a specified time or place.
-
B.
wasFoundedBy
chosen
Indicates that an organization, institution, or entity came into existence through the initiating action or establishment by a specific founder or founding group.
-
C.
createdByStudioFounder
Indicates that something (such as a work, project, or company) was created by the person who founded the studio.
-
D.
coFounderOfProducingCompany
Indicates that an entity is a co-founder of a particular producing company, sharing founding responsibility with one or more others.
-
E.
founderKnownFor
Indicates that a founder is particularly recognized or notable for a specific work, achievement, product, or contribution.
- F. None of above.
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_69f077ef00fc81909325f084ad37c035 |
completed | April 28, 2026, 9:03 a.m. |
| NER | Named-entity recognition | batch_69fccdd496048190bca801a8a9eecb62 |
completed | May 7, 2026, 5:37 p.m. |
| PD | Predicate disambiguation | batch_69fcccee6240819084680887731ff64b |
completed | May 7, 2026, 5:33 p.m. |
Created at: April 28, 2026, 9:51 a.m.