Triple
T16261819
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pride Fighting Championships |
E394771
|
entity |
| Predicate | featuredFighter |
P101800
|
FINISHED |
| Object | Mark Coleman |
E1048119
|
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: Mark Coleman | Statement: [Pride Fighting Championships, featuredFighter, Mark Coleman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Coleman Context triple: [Pride Fighting Championships, featuredFighter, Mark Coleman]
-
A.
Mark Coleman
chosen
Mark Coleman is an American mixed martial artist and former UFC heavyweight champion widely regarded as a pioneer of ground-and-pound fighting.
-
B.
Jeff Coleman
Jeff Coleman is the namesake of Coleman Coliseum, a prominent multi-purpose arena at the University of Alabama.
-
C.
John Coleman
John Coleman was a legendary Australian rules footballer renowned as one of Essendon Football Club’s greatest full-forwards and most prolific goal scorers.
-
D.
John Coleman
John Coleman was an American television meteorologist and entrepreneur best known for co-founding and serving as the first CEO of The Weather Channel.
-
E.
Rob Coleman
Rob Coleman is a visual effects supervisor and animation director best known for his work on major films at Industrial Light & Magic, including the Star Wars prequel trilogy.
- 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_69d87f221d8081909b0b2063e7528ba2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e245c4a0b08190af3574f087205afc |
completed | April 17, 2026, 2:37 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a006ecc2b4c8190ac9654ac826f198e |
completed | May 10, 2026, 11:41 a.m. |
Created at: April 10, 2026, 5:04 a.m.