Triple
T29234899
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tanzania national football team |
E741166
|
entity |
| Predicate | cecafaCupTitles |
P166445
|
FINISHED |
| Object | 3 |
—
|
LITERAL 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: 3 | Statement: [Tanzania national football team, cecafaCupTitles, 3]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: cecafaCupTitles Context triple: [Tanzania national football team, cecafaCupTitles, 3]
-
A.
cecaafaCupTitles
chosen
Indicates that an entity has won one or more CECAFA Cup titles.
-
B.
goldCupTitles
Indicates the number of CONCACAF Gold Cup titles that an entity (typically a team or country) has won.
-
C.
FIFAConfederationsCupTitleYear
Indicates the specific year in which an entity won a FIFA Confederations Cup title.
-
D.
gulfCupTitles
Indicates the number of Gulf Cup championship titles an entity (typically a national football team) has won.
-
E.
ConfederationsCupTitles
Indicates the number of FIFA Confederations Cup championships an entity has won.
- 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_69f0911dd6fc819097d1abb287016489 |
completed | April 28, 2026, 10:51 a.m. |
| NER | Named-entity recognition | batch_69f6646309648190806dece783dd9e55 |
completed | May 2, 2026, 8:53 p.m. |
| PD | Predicate disambiguation | batch_69f660f2e3708190ab658652bcfc04d0 |
completed | May 2, 2026, 8:39 p.m. |
Created at: April 28, 2026, 12:28 p.m.