Triple
T19523671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Latvian Football Federation |
E488465
|
entity |
| Predicate | shortName |
P43
|
FINISHED |
| Object | LFF |
—
|
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: LFF | Statement: [Latvian Football Federation, shortName, LFF]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: LFF Context triple: [Latvian Football Federation, shortName, LFF]
-
A.
LFF
LFF is the commonly used abbreviation for the BFI London Film Festival, a major annual international film festival held in London.
-
B.
LFF
chosen
LFF is the commonly used abbreviation for the Libyan Football Federation, the governing body for football in Libya.
-
C.
LFFN
LFFN is the ICAO airport code for Brienne-le-Château airfield, a small airfield in northeastern France.
-
D.
PÖFF
PÖFF is the Tallinn Black Nights Film Festival, a major international film festival held annually in Estonia’s capital and one of the largest in Northern Europe.
-
E.
BFI
BFI is a University of Chicago research institute that advances economic scholarship and policy through data-driven, market-oriented research.
- 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_69d8e8da8bec819081f400199491ccc3 |
completed | April 10, 2026, 12:11 p.m. |
| NER | Named-entity recognition | batch_69e636392444819094f6a2aa1cdf3d42 |
completed | April 20, 2026, 2:20 p.m. |
Created at: April 10, 2026, 1:41 p.m.