Triple
T22784683
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Prix Goncourt des Lycéens |
E563932
|
entity |
| Predicate | sponsor |
P67
|
FINISHED |
| Object | Fnac |
—
|
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: Fnac | Statement: [Prix Goncourt des Lycéens, sponsor, Fnac]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Fnac Context triple: [Prix Goncourt des Lycéens, sponsor, Fnac]
-
A.
Fnac
chosen
Fnac is a major French retail chain specializing in cultural and electronic products such as books, music, films, and consumer electronics.
-
B.
Xnet
Xnet is the underground, encrypted peer-to-peer communication network used by teens to evade government surveillance in Cory Doctorow’s novel "Little Brother."
-
C.
Macroplaza
Macroplaza is a vast central square and civic complex in downtown Monterrey, Mexico, known for its monuments, gardens, and surrounding government and cultural buildings.
-
D.
Zalando
Zalando is a leading European online fashion and lifestyle retailer known for offering a wide range of clothing, shoes, and accessories from numerous brands.
-
E.
Kogan
Kogan is a small rural town in Queensland, Australia, known for its agricultural activities and role in the Western Downs Region’s energy and resource industries.
- 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_69e2455500788190b4b33030461f3bbd |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17c30b4dc8190a5e23f4ce7feb300 |
completed | April 29, 2026, 3:34 a.m. |
Created at: April 17, 2026, 3:29 p.m.