Triple
T20559393
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Agfa film production |
E504805
|
entity |
| Predicate | notableProduct |
P1448
|
FINISHED |
| Object | Agfa APX |
—
|
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: Agfa APX | Statement: [Agfa film production, notableProduct, Agfa APX]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Agfa APX Context triple: [Agfa film production, notableProduct, Agfa APX]
-
A.
AgfaPhoto
AgfaPhoto is a consumer imaging brand known for photographic film, cameras, and related imaging products, originating from the former Agfa-Gevaert photo business.
-
B.
Agfa
chosen
Agfa is a historic German company best known for its photographic films, cameras, and imaging technologies.
-
C.
APF
APF is the commonly used acronym for the Parliamentary Assembly of La Francophonie, an international organization that brings together parliamentarians from French-speaking countries to promote the French language, democracy, and human rights.
-
D.
APF
APF is the acronym for the Asociación Paraguaya de Fútbol, the governing body of professional and amateur football in Paraguay.
-
E.
APF
APF is the IATA airport code for Naples Municipal Airport, a public airport serving Naples, Florida.
- 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_69e0b4b6587c8190aee63dc7cff244ea |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6a5e178648190910795bae5422e50 |
completed | April 20, 2026, 10:17 p.m. |
Created at: April 16, 2026, 11:38 a.m.