Triple
T27545609
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | KOR |
E695351
|
entity |
| Predicate | FIFATrigrammeFor |
P6278
|
FINISHED |
| Object | South Korea national football team |
—
|
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: South Korea national football team | Statement: [KOR, FIFATrigrammeFor, South Korea national football team]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: FIFATrigrammeFor Context triple: [KOR, FIFATrigrammeFor, South Korea national football team]
-
A.
fifaTrigrammeStatusAfterDissolution
Indicates the status assigned to a country's FIFA trigram code after the dissolution of that country or its football association.
-
B.
FIFAcode
chosen
Indicates the standardized three-letter country or territory code assigned by FIFA to represent a national football team in international competitions.
-
C.
numberOfTrigrams
Indicates the total count of distinct three-character or three-token sequences (trigrams) associated with or contained in the given entity.
-
D.
FIFATournament
Indicates a relationship where an entity is recognized as a tournament organized, sanctioned, or officially associated with FIFA.
-
E.
hasThreeLetterForm
Indicates that an entity’s written or symbolic form consists of exactly three letters.
- F. None of above.
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_69ef5386c3e08190bfe33aa326e1f72b |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62f840a588190919f31170d31b0c9 |
completed | May 2, 2026, 5:08 p.m. |
| PD | Predicate disambiguation | batch_69f62c1762f881908c25e8f70ecd5041 |
completed | May 2, 2026, 4:53 p.m. |
Created at: April 27, 2026, 1:33 p.m.