Triple
T23165651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 4 |
E578704
|
entity |
| Predicate | featuredFighter |
P101800
|
FINISHED |
| Object | Marcus Bossett |
—
|
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: Marcus Bossett | Statement: [UFC 4, featuredFighter, Marcus Bossett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marcus Bossett Context triple: [UFC 4, featuredFighter, Marcus Bossett]
-
A.
Marcus Bossett
chosen
Marcus Bossett is a mixed martial artist best known for competing in the early Ultimate Fighting Championship events during the 1990s.
-
B.
Chris Hoy
Chris Hoy is an American politician who serves as the mayor of Salem, Oregon.
-
C.
Chris Hoy
Chris Hoy is a British former track cyclist and multiple Olympic and world champion, widely regarded as one of the most successful cyclists in history.
-
D.
Scott Brash
Scott Brash is a British Olympic gold medal-winning show jumping rider and former world number one, renowned for his success in major international competitions.
-
E.
David Weir
David Weir is a British Paralympic wheelchair racer and multiple gold medalist renowned for his achievements on the track and in major marathons.
- 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_69e245fc75348190a0288401044c8af8 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18f2bca4881909f6148d588948018 |
completed | April 29, 2026, 4:55 a.m. |
Created at: April 17, 2026, 4:03 p.m.