Triple
T1826963
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 FIFA World Cup matches |
E40673
|
entity |
| Predicate | previousEditionMatches |
P10856
|
FINISHED |
| Object | 2014 FIFA World Cup matches |
—
|
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: 2014 FIFA World Cup matches | Statement: [2018 FIFA World Cup matches, previousEditionMatches, 2014 FIFA World Cup matches]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousEditionMatches Context triple: [2018 FIFA World Cup matches, previousEditionMatches, 2014 FIFA World Cup matches]
-
A.
previousFinals
Indicates that one entity represents a past or prior finals event or appearance in relation to another entity.
-
B.
previousGames
chosen
Indicates that one entity represents games that occurred earlier in time relative to another entity.
-
C.
runnerUpPreviousAppearance
Indicates that an entity finished as the runner-up in its immediately preceding appearance or participation in a given event or context.
-
D.
previousSeason
Indicates that one season directly precedes another in chronological order within the same series or competition.
-
E.
previousWorldSeries
Indicates that one World Series event immediately precedes another in chronological order.
- 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_69a8864644bc8190b2358ab897194ac1 |
completed | March 4, 2026, 7:21 p.m. |
| NER | Named-entity recognition | batch_69abb45402688190b9a535b14030c354 |
completed | March 7, 2026, 5:15 a.m. |
| PD | Predicate disambiguation | batch_69abafd6a9948190ac2b2743db6f8f69 |
completed | March 7, 2026, 4:55 a.m. |
Created at: March 4, 2026, 7:32 p.m.