Triple
T10023757
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Fédération Équestre Internationale |
E200673
|
entity |
| Predicate | hasAbbreviation |
P43
|
FINISHED |
| Object | FEI |
E835246
|
NE FINISHED |
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: FEI | Statement: [Fédération Équestre Internationale, hasAbbreviation, FEI]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: FEI Context triple: [Fédération Équestre Internationale, hasAbbreviation, FEI]
-
A.
FEI
chosen
FEI is the international governing body for equestrian sports, overseeing disciplines such as show jumping, dressage, and eventing worldwide.
-
B.
FEI General Assembly
The FEI General Assembly is the annual gathering of the Fédération Equestre Internationale’s member federations, where major decisions and policies for international equestrian sport are debated and voted on.
-
C.
Erfe
Erfe is the surname of Elaine Mendoza Erfe, best known as the wife of American comedian Dave Chappelle.
-
D.
Fiser
Fiser is a surname variant of Fischer, commonly associated with Central or Eastern European origins.
-
E.
Efficeon
Efficeon is a family of low-power, x86-compatible microprocessors developed by Transmeta as the successor to its Crusoe line, aimed primarily at mobile and embedded computing devices.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca831c45f08190ac1505cc15076608 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cdcd7c75548190aa604d90d63dc111 |
completed | April 2, 2026, 1:59 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d28222773c81908eb84974fd6ce106 |
completed | April 5, 2026, 3:39 p.m. |
Created at: March 30, 2026, 8:53 p.m.