Triple
T15883278
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2009 NBA All-Star Game |
E385126
|
entity |
| Predicate | eastHeadCoach |
P33087
|
FINISHED |
| Object | Mike Brown |
E89461
|
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: Mike Brown | Statement: [2009 NBA All-Star Game, eastHeadCoach, Mike Brown]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mike Brown Context triple: [2009 NBA All-Star Game, eastHeadCoach, Mike Brown]
-
A.
Mike Brown
chosen
Mike Brown is an American basketball coach best known for leading the Cleveland Cavaliers during the early years of LeBron James’s career and for his defensive-minded coaching style.
-
B.
Mike Brown
Mike Brown is an American football executive best known as the longtime owner and de facto general manager of the NFL’s Cincinnati Bengals.
-
C.
Michael Shoemaker
Michael Shoemaker is an American television producer and writer best known for his long-running work on late-night comedy shows, including collaborations with Jimmy Fallon.
-
D.
Michael Shoemaker
Michael Shoemaker is an illustrator best known for his artwork in the book "Thank You Notes."
-
E.
Craig Heisinger
Craig Heisinger is a Canadian ice hockey executive best known for his long-time leadership role with the Manitoba Moose organization.
- 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_69d86da4e86481909f1325fdc971b5ec |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e156186b98819087b80ade6bd71a69 |
completed | April 16, 2026, 9:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffa95466e08190a967114821651e60 |
completed | May 9, 2026, 9:38 p.m. |
Created at: April 10, 2026, 4:51 a.m.