Triple
T4134689
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Irish Football Association |
E85124
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | IFA |
E281149
|
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: IFA | Statement: [Irish Football Association, shortName, IFA]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: IFA Context triple: [Irish Football Association, shortName, IFA]
-
A.
IFA
chosen
IFA is the Irish Football Association, the governing body responsible for organizing and overseeing football in Northern Ireland.
-
B.
FiAF
FiAF is the commonly used abbreviation for the Finnish Air Force, the air warfare branch of Finland’s Defence Forces.
-
C.
EIF
EIF is the commonly used abbreviation for the Edinburgh International Festival, a major annual performing arts festival held in Scotland’s capital city.
-
D.
EIF
EIF is the European Investment Fund, an EU institution that supports small and medium-sized enterprises by providing risk finance through financial intermediaries.
-
E.
IDA
IDA is the International Development Association, the World Bank Group’s fund that provides concessional loans and grants to the world’s poorest countries.
- 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_69aed935ccd881909dc61f81bcdb7a78 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af023190608190bcc929c5996b7378 |
completed | March 9, 2026, 5:24 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b576c75e5c8190acc4ee72cb574432 |
completed | March 14, 2026, 2:55 p.m. |
Created at: March 9, 2026, 3:43 p.m.