Triple
T3078545
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2018 NWSL Championship |
E64198
|
entity |
| Predicate | coachOfWinningTeam |
P10030
|
FINISHED |
| Object | Paul Riley |
E24600
|
NE 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: Paul Riley | Statement: [2018 NWSL Championship, coachOfWinningTeam, Paul Riley]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paul Riley Context triple: [2018 NWSL Championship, coachOfWinningTeam, Paul Riley]
-
A.
Paul Riley
chosen
Paul Riley is an English-born soccer coach best known for his tenure in U.S. women’s professional soccer, including a controversial spell leading top NWSL clubs.
-
B.
Paul Silas
Paul Silas was an American professional basketball player and three-time NBA champion who later became a head coach in the league.
-
C.
Paul Westphal
Paul Westphal was an American Hall of Fame basketball player and coach best known as an All-Star guard for the Phoenix Suns in the 1970s.
-
D.
Roy Tarpley
Roy Tarpley was an American professional basketball player, best known as a talented but troubled Dallas Mavericks big man whose NBA career was derailed by substance abuse issues.
-
E.
Bill Thomas
Bill Thomas was an American costume designer known for his work on numerous Hollywood films, including classic melodramas of the 1950s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
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_69ad857bb4c88190a4cf27893fcabed8 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada1a86a848190a47ca127cc7e6326 |
completed | March 8, 2026, 4:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b276df42048190bcb79277a28f866a |
completed | March 12, 2026, 8:18 a.m. |
Created at: March 8, 2026, 3:02 p.m.