Triple
T13263486
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | UFC 91 |
E315856
|
entity |
| Predicate | fighterOnCard |
P109204
|
FINISHED |
| Object |
Ryan Thomas
Ryan Thomas is a professional mixed martial artist who has competed in major promotions including the UFC.
|
E1030785
|
NE FINISHED |
How this triple was built (4 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: Ryan Thomas | Statement: [UFC 91, fighterOnCard, Ryan Thomas]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ryan Thomas Context triple: [UFC 91, fighterOnCard, Ryan Thomas]
-
A.
Ryan Thomas
Ryan Thomas is a fictional character portrayed by actor Kerr Smith, best known from his work in American television dramas.
-
B.
Jay Thomas
Jay Thomas was an American actor and comedian known for his roles on television series such as "Cheers" and "Murphy Brown," as well as in various films.
-
C.
Sean Patrick Thomas
Sean Patrick Thomas is an American actor best known for his roles in films like "Save the Last Dance" and television series such as "The District."
-
D.
Brandon Thomas
Brandon Thomas was a British playwright best known for writing the classic farce "Charley's Aunt," which has been widely adapted for stage and screen.
-
E.
Drew Thomas
Drew Thomas is a fictional character played by South African-Canadian actor Shannon Kook, best known from the horror film franchise "The Conjuring."
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ryan Thomas Triple: [UFC 91, fighterOnCard, Ryan Thomas]
Generated description
Ryan Thomas is a professional mixed martial artist who has competed in major promotions including the UFC.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ryan Thomas Target entity description: Ryan Thomas is a professional mixed martial artist who has competed in major promotions including the UFC.
-
A.
Ryan Thomas
Ryan Thomas is a fictional character portrayed by actor Kerr Smith, best known from his work in American television dramas.
-
B.
Jay Thomas
Jay Thomas was an American actor and comedian known for his roles on television series such as "Cheers" and "Murphy Brown," as well as in various films.
-
C.
Sean Patrick Thomas
Sean Patrick Thomas is an American actor best known for his roles in films like "Save the Last Dance" and television series such as "The District."
-
D.
Brandon Thomas
Brandon Thomas was a British playwright best known for writing the classic farce "Charley's Aunt," which has been widely adapted for stage and screen.
-
E.
Drew Thomas
Drew Thomas is a fictional character played by South African-Canadian actor Shannon Kook, best known from the horror film franchise "The Conjuring."
- F. None of above. chosen
Provenance (5 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_69d806b1d9ac8190852c5571d5bd5f0f |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dadcd4cb008190af99c4856e76ac08 |
completed | April 11, 2026, 11:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f70a48bc488190a5cf692d81bdcbba |
completed | May 3, 2026, 8:41 a.m. |
| NEDg | Description generation | batch_69f70b5dbcc4819081b5ba410e319eb7 |
completed | May 3, 2026, 8:46 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69f70c4c6f908190b2ebc2a90b049e59 |
completed | May 3, 2026, 8:50 a.m. |
Created at: April 9, 2026, 9:25 p.m.