Triple
T4573451
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Francois Pienaar |
E123088
|
entity |
| Predicate | lastTestForNationalTeam |
P37874
|
FINISHED |
| Object | 1996 |
—
|
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: 1996 | Statement: [Francois Pienaar, lastTestForNationalTeam, 1996]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: lastTestForNationalTeam Context triple: [Francois Pienaar, lastTestForNationalTeam, 1996]
-
A.
previousNationalTeamEntity
Indicates that an entity previously represented a particular national team before its current or later affiliation.
-
B.
nationalTeamLastAppearance
chosen
Indicates the most recent occasion on which an entity appeared for its national team in an official match or competition.
-
C.
hasPlayedForNationalTeam
Indicates that an athlete has been a member of and appeared in competition for a specified national team.
-
D.
associatedWithNationalTeam
Indicates that an entity has a formal connection or involvement with a specific national team, such as playing for, coaching, or otherwise being officially linked to it.
-
E.
nationalTeamSystem
Indicates a relationship where an entity is part of, governed by, or operates within a specific national team structure or organizational system.
- 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_69bd46466c7081909d07f36be2d08804 |
completed | March 20, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69bd58c89a5c81909a78bf0ac64777ad |
completed | March 20, 2026, 2:25 p.m. |
| PD | Predicate disambiguation | batch_69bd5227063c8190973155a875b013a7 |
completed | March 20, 2026, 1:56 p.m. |
Created at: March 20, 2026, 1:10 p.m.