Triple
T21803030
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | AFNOR |
E538282
|
entity |
| Predicate | abbreviation |
P43
|
FINISHED |
| Object | AFNOR |
—
|
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: AFNOR | Statement: [AFNOR, abbreviation, AFNOR]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: AFNOR Context triple: [AFNOR, abbreviation, AFNOR]
-
A.
AFNOR
chosen
AFNOR is the French national organization responsible for developing and promoting standards across industry, services, and public sectors.
-
B.
Joint Staff of the French Armed Forces
The Joint Staff of the French Armed Forces is the central military command body responsible for planning, coordinating, and directing France’s armed forces under the authority of the Chief of the Defence Staff.
-
C.
MACIF
MACIF is a major French mutual insurance company known for offering a wide range of insurance and financial services to individuals and businesses.
-
D.
ONERA
ONERA is the French national aerospace research center, specializing in aeronautics, space, and defense technologies.
-
E.
ARCOM (France)
ARCOM (France) is the French independent authority responsible for regulating audiovisual and digital communication, including television, radio, and online platforms.
- 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_69e0c4733f4081909a86622e7e6d15d2 |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69f0780062688190a6c3a2a0364f0f77 |
completed | April 28, 2026, 9:04 a.m. |
Created at: April 16, 2026, 6:53 p.m.