Triple
T6378969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thin Lizzy |
E143534
|
entity |
| Predicate | hasPart |
P35
|
FINISHED |
| Object | Brian Downey |
E362693
|
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: Brian Downey | Statement: [Thin Lizzy, hasPart, Brian Downey]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brian Downey Context triple: [Thin Lizzy, hasPart, Brian Downey]
-
A.
Brian Downey
chosen
Brian Downey is an Irish drummer best known as a founding member of the hard rock band Thin Lizzy.
-
B.
Chris Downey
Chris Downey is a television writer and producer best known for co-creating the crime drama series "Leverage."
-
C.
Glen Downey
Glen Downey is a Canadian author and educator known for his work in graphic novels and educational publishing, particularly in literacy and comics-based learning.
-
D.
Juan Downey
Juan Downey was a Chilean video and conceptual artist known for his pioneering work in interactive video, performance, and media art that explored identity, technology, and Latin American culture.
-
E.
Kevin Dowd
Kevin Dowd is the brother of Pulitzer Prize–winning New York Times columnist Maureen Dowd.
- 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_69c008d9f4348190ab598a2913259a1c |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0685029488190911fb24c470b6f0d |
completed | March 22, 2026, 10:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c6637a1b548190b5af5cbae81346e8 |
completed | March 27, 2026, 11:01 a.m. |
Created at: March 22, 2026, 4:33 p.m.