Triple
T6446839
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robbie Lawler |
E138362
|
entity |
| Predicate | hasFought |
P30824
|
FINISHED |
| Object | Carlos Condit |
E568780
|
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: Carlos Condit | Statement: [Robbie Lawler, hasFought, Carlos Condit]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carlos Condit Context triple: [Robbie Lawler, hasFought, Carlos Condit]
-
A.
Carlos Condit
chosen
Carlos Condit is an American mixed martial artist and former UFC Interim Welterweight Champion known for his aggressive striking and finishing ability.
-
B.
Ronda Rousey
Ronda Rousey is an American professional wrestler, former mixed martial arts champion, and Olympic judoka who gained fame in the UFC before becoming a top star in WWE.
-
C.
Leona Philippo
Leona Philippo is a Dutch singer and performer who gained national fame after winning the popular televised talent competition The Voice of Holland.
-
D.
Daniela Andrade
Daniela Andrade is a Canadian singer-songwriter and YouTube artist known for her intimate acoustic covers and original indie-pop music.
-
E.
Jasmine Crockett
Jasmine Crockett is an American Democratic politician and attorney serving in the U.S. House of Representatives from Texas.
- 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_69c008aa61ac8190bc96715ed79fe2d8 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c0698edeac81909426902471d8a57b |
completed | March 22, 2026, 10:13 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c65392a6c08190b868fab12260d6c2 |
completed | March 27, 2026, 9:53 a.m. |
Created at: March 22, 2026, 4:46 p.m.