Triple
T10070734
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Matt Hughes |
E213615
|
entity |
| Predicate | notableVictoryOver |
P34090
|
FINISHED |
| Object | Frank Trigg |
E941212
|
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: Frank Trigg | Statement: [Matt Hughes, notableVictoryOver, Frank Trigg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Frank Trigg Context triple: [Matt Hughes, notableVictoryOver, Frank Trigg]
-
A.
Frank Trigg
chosen
Frank Trigg is an American mixed martial artist and former UFC welterweight title challenger known for his high-profile bouts in the early 2000s.
-
B.
Boyd Tinsley
Boyd Tinsley is an American violinist and composer best known as a longtime member of the Dave Matthews Band.
-
C.
Burley Mitchell
Burley Mitchell is a former Chief Justice of the North Carolina Supreme Court and a prominent American jurist.
-
D.
Frank Tripp
Frank Tripp is a tough, no-nonsense Miami-Dade homicide detective on the television series CSI: Miami, known for his dry wit and steady support of the CSI team.
-
E.
Allan Shivers
Allan Shivers was a mid-20th-century American politician who served as governor of Texas and was influential in the state's conservative Democratic politics.
- 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_69ca839add308190b57d53b4ec21f2d0 |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cdcffa045c8190a08db0bb74cb006a |
completed | April 2, 2026, 2:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f1658e03a8819098ea2ac2f818a61a |
completed | April 29, 2026, 1:57 a.m. |
Created at: March 30, 2026, 8:59 p.m.