Triple
T21748788
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Claire Denis |
E536855
|
entity |
| Predicate | educatedAt |
P5
|
FINISHED |
| Object | IDHEC |
—
|
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: IDHEC | Statement: [Claire Denis, educatedAt, IDHEC]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IDHEC Context triple: [Claire Denis, educatedAt, IDHEC]
-
A.
IDHEC
chosen
IDHEC (Institut des hautes études cinématographiques) was a prestigious French film school in Paris that trained many notable filmmakers and industry professionals.
-
B.
Icade Santé
Icade Santé is a French real estate company specializing in healthcare facilities such as hospitals and clinics.
-
C.
INSA Lyon
INSA Lyon is a leading French grande école and engineering school located near Lyon, renowned for its strong research activity and multidisciplinary engineering programs.
-
D.
Technopôle
Technopôle is a tramway terminus in Rouen, France, serving a technology and business park area.
-
E.
Adolphe Merkle Institute
Adolphe Merkle Institute is a Swiss research center at the University of Fribourg specializing in interdisciplinary nanoscience and materials science.
- 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_69e0c46eab808190b848242d63a17c47 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f01a78bd908190b74e26ab1cc8788f |
completed | April 28, 2026, 2:24 a.m. |
Created at: April 16, 2026, 6:50 p.m.