Triple
T14541015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Year 3000 |
E341167
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object | Matt Willis |
E889056
|
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: Matt Willis | Statement: [Year 3000, writer, Matt Willis]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Matt Willis Context triple: [Year 3000, writer, Matt Willis]
-
A.
Matt Willis
chosen
Matt Willis is an English musician, singer, and television personality best known as the bassist and co-vocalist of the pop rock band Busted.
-
B.
Justin Wilkes
Justin Wilkes is a television producer and creator known for developing the series "Mars" and other documentary and scripted projects.
-
C.
Joe Willis
Joe Willis is an American professional soccer goalkeeper in Major League Soccer who has been recognized as one of the league’s top performers at his position.
-
D.
Tim Willits
Tim Willits is a video game designer best known as a longtime id Software developer and creative lead on major first-person shooters such as the Quake and Doom series.
-
E.
Dave Wilkins
Dave Wilkins is a musician best known as a member of the Australian rock band 30 Odd Foot of Grunts, which was fronted by actor Russell Crowe.
- 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_69d822db9c8481908213ceb39585f792 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb1bd0dd4819094c8b2f2aa6b1c5e |
completed | April 14, 2026, 9:29 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fda9107e9c8190850716c21e627a39 |
completed | May 8, 2026, 9:12 a.m. |
Created at: April 10, 2026, 1:22 a.m.