Triple
T23203204
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Landsliðið |
E580373
|
entity |
| Predicate | governingBodyAbbreviation |
P2886
|
FINISHED |
| Object | FSF |
—
|
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: FSF | Statement: [Landsliðið, governingBodyAbbreviation, FSF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FSF Context triple: [Landsliðið, governingBodyAbbreviation, FSF]
-
A.
FSF
chosen
FSF is the Faroese Football Association, the governing body responsible for organizing and overseeing football activities in the Faroe Islands.
-
B.
FSF
FSF is the governing body responsible for overseeing and organizing football activities and national teams in Senegal.
-
C.
FSF
FSF is the station code for Fassifern railway station in New South Wales, Australia.
-
D.
Free Software Foundation Europe
Free Software Foundation Europe is a non-profit organization that promotes and defends free and open source software, digital rights, and user freedoms across Europe.
-
E.
Free Software Foundation
The Free Software Foundation is a nonprofit organization that promotes computer users' freedom and defends the rights of all software users through advocacy, licensing, and development of free software.
- 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_69e24602ae1481908aaa6bc7ca493867 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1907a8bb48190846802a24d33bccf |
completed | April 29, 2026, 5 a.m. |
Created at: April 17, 2026, 4:07 p.m.