Triple
T10103018
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Garrincha |
E216247
|
entity |
| Predicate | worldCupMatchesWithoutDefeat |
P92436
|
FINISHED |
| Object | never lost a World Cup match he started |
—
|
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: never lost a World Cup match he started | Statement: [Garrincha, worldCupMatchesWithoutDefeat, never lost a World Cup match he started]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: worldCupMatchesWithoutDefeat Context triple: [Garrincha, worldCupMatchesWithoutDefeat, never lost a World Cup match he started]
-
A.
worldCupWon
Indicates that the subject has won the FIFA World Cup tournament.
-
B.
worldCupPlayed
Indicates that a World Cup tournament has taken place or been held (typically at a specific time and/or location).
-
C.
WorldCupVictories
Indicates the number of times an entity has won the FIFA World Cup tournament.
-
D.
AustraliaWorldCupTitlesAfterMatch
Indicates the number of World Cup titles Australia has won after the completion of a specific match.
-
E.
worldCupFinalAppearance
Indicates that an entity has participated in the final match of a FIFA World Cup tournament.
- F. None of above. chosen
Provenance (4 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_69ca83d039f08190b9d10363221c69fb |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cdd09af07c819099774af46ebf62d7 |
completed | April 2, 2026, 2:12 a.m. |
| PD | Predicate disambiguation | batch_69cd4b9b853c8190a2af993ce9b21309 |
completed | April 1, 2026, 4:45 p.m. |
| PDg | Predicate description generation | batch_69cd5150ae98819086c4f822114b4e2c |
completed | April 1, 2026, 5:09 p.m. |
Created at: March 30, 2026, 9:02 p.m.