Triple
T13322336
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Burn |
E317343
|
entity |
| Predicate | musicVideoDirector |
P4911
|
FINISHED |
| Object | Jake Nava |
E69967
|
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: Jake Nava | Statement: [Burn, musicVideoDirector, Jake Nava]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jake Nava Context triple: [Burn, musicVideoDirector, Jake Nava]
-
A.
Jake Nava
chosen
Jake Nava is a British music video director known for his visually striking work with major artists across pop and R&B.
-
B.
Darrin Navarro
Darrin Navarro is a film editor known for his work on feature films such as "Brain on Fire."
-
C.
Mike Navarro
Mike Navarro is a relative of American guitarist Dave Navarro, known for his work with Jane's Addiction and the Red Hot Chili Peppers.
-
D.
Chris Núñez
Chris Núñez is a renowned American tattoo artist and television personality best known for co-hosting the reality competition series "Miami Ink" and serving as a judge on "Ink Master."
-
E.
Mark Dacascos
Mark Dacascos is an American actor and martial artist known for his roles in action films and television, as well as for serving as the Chairman on the TV show "Iron Chef America."
- 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_69d806b4d62c81908d4ced1665414be5 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69d9992ab83c8190982d9f54dff6919f |
completed | April 11, 2026, 12:43 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f76b9c0c088190ba18b5c631bcc365 |
completed | May 3, 2026, 3:37 p.m. |
Created at: April 9, 2026, 9:30 p.m.