Triple
T17827216
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brian Labone |
E445150
|
entity |
| Predicate | name |
P16
|
FINISHED |
| Object | Brian Labone |
—
|
NE NERFINISHED |
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: Brian Labone | Statement: [Brian Labone, name, Brian Labone]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brian Labone Context triple: [Brian Labone, name, Brian Labone]
-
A.
Brian Labone
chosen
Brian Labone was an English footballer best known as a long-serving central defender and captain for Everton and a World Cup-winning squad member with England in 1966.
-
B.
Josh Sborz
Josh Sborz is an American professional baseball pitcher known for his standout collegiate career at the University of Virginia, where he helped lead the Cavaliers to a national championship.
-
C.
Brian Latture
Brian Latture is a music producer known for his work on LL Cool J’s 1989 hip hop album "Walking with a Panther."
-
D.
Brian Lando
Brian Lando is a television producer best known for his behind-the-scenes leadership on reality and unscripted series, including work on the show "Candidly Nicole."
-
E.
Brian Mahoney
Brian Mahoney is an actor best known for his role in the cult crime film "The Boondock Saints."
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8b9f1a6d881909f024bc603111cdb |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e48914e20481908883d1da194f446c |
completed | April 19, 2026, 7:49 a.m. |
Created at: April 10, 2026, 10:15 a.m.