Triple
T21871990
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Yes (Union era) |
E540024
|
entity |
| Predicate | hasMember |
P10
|
FINISHED |
| Object | Alan White |
—
|
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: Alan White | Statement: [Yes (Union era), hasMember, Alan White]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alan White Context triple: [Yes (Union era), hasMember, Alan White]
-
A.
Alan White
chosen
Alan White was an English rock drummer best known for his long tenure with the progressive rock band Yes and for playing on John Lennon’s “Imagine.”
-
B.
Alan White
Alan White is an English drummer best known for his long tenure with the rock band Oasis during their peak years in the 1990s and early 2000s.
-
C.
Tommy Weir
Tommy Weir is a relatively obscure individual whose primary public mention is as a namesake associated with the surname Weir.
-
D.
Jon Davison
Jon Davison is a British video game journalist and media executive known for his work at outlets such as GamePro, 1UP, and IGN.
-
E.
Jon Davison
Jon Davison is an American film producer best known for his work on satirical and science fiction films such as "Starship Troopers" and "RoboCop."
- 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_69e0c478f59081909d54302b57fc1ce3 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f0f3368d488190a37224b587858ab0 |
completed | April 28, 2026, 5:49 p.m. |
Created at: April 16, 2026, 6:59 p.m.