Triple
T6328893
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | PGA of America |
E141925
|
entity |
| Predicate | roleInRyderCup |
P33874
|
FINISHED |
| Object | selects U.S. Ryder Cup captain |
—
|
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: selects U.S. Ryder Cup captain | Statement: [PGA of America, roleInRyderCup, selects U.S. Ryder Cup captain]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: roleInRyderCup Context triple: [PGA of America, roleInRyderCup, selects U.S. Ryder Cup captain]
-
A.
roleInRugby
Indicates the specific position or function an entity holds within the context of playing or participating in rugby.
-
B.
sportingRoleRecognised
Indicates that a particular sporting role or position has been formally acknowledged or accepted as valid within a given context or system.
-
C.
competitionRole
chosen
Indicates that an entity holds a specific role, position, or function within a competitive event or contest.
-
D.
playsInDerbyWith
Indicates that two entities participate together as opponents or competitors in the same derby event or match.
-
E.
roleInTourDeFrance
Indicates the specific capacity or function an entity has within the context of the Tour de France (e.g., rider, team, official, or support role).
- 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_69c008d201748190917e69c41ba3f978 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0651197908190a30e504e2442d40f |
completed | March 22, 2026, 9:54 p.m. |
| PD | Predicate disambiguation | batch_69c060e7e2d48190af9d004236466788 |
completed | March 22, 2026, 9:36 p.m. |
Created at: March 22, 2026, 4:29 p.m.