Triple
T4538134
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1970 NBA Finals |
E107458
|
entity |
| Predicate | coachOfRunnerUp |
P2169
|
FINISHED |
| Object | Joe Mullaney |
E167181
|
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: Joe Mullaney | Statement: [1970 NBA Finals, coachOfRunnerUp, Joe Mullaney]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Mullaney Context triple: [1970 NBA Finals, coachOfRunnerUp, Joe Mullaney]
-
A.
Joe Mullaney
chosen
Joe Mullaney was a prominent American basketball coach known for his successful stints in college basketball and the ABA, including leading the Kentucky Colonels.
-
B.
Tommy Mullaney
Tommy Mullaney is a fictional character portrayed by John Spencer, best known as a gruff but skilled public defender on the television series L.A. Law.
-
C.
Eddie Cahill
Eddie Cahill is an American actor best known for his role as Detective Don Flack on the television series CSI: NY.
-
D.
Michael Maloney
Michael Maloney is a British actor known for his work in film, television, and theatre, including prominent roles in Shakespearean adaptations.
-
E.
Jack Mulligan
Jack Mulligan is a corrupt and ambitious Chicago politician who serves as a central antagonist in the heist thriller film "Widows" (2018).
- 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_69bd43f922788190b7edfa294e39b178 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd57b8c4788190b35d110553013ff1 |
completed | March 20, 2026, 2:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69bdfa1681708190ae4dc66e8734e5a1 |
completed | March 21, 2026, 1:53 a.m. |
Created at: March 20, 2026, 1:04 p.m.