Triple
T12906648
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amazing |
E308745
|
entity |
| Predicate | musicVideoDirector |
P4911
|
FINISHED |
| Object | Marty Callner |
E372907
|
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: Marty Callner | Statement: [Amazing, musicVideoDirector, Marty Callner]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marty Callner Context triple: [Amazing, musicVideoDirector, Marty Callner]
-
A.
Marty Callner
chosen
Marty Callner is an American television and music video director known for his work on high-profile comedy specials and iconic rock music videos.
-
B.
Bill Callery
Bill Callery is an American songwriter best known for his work in country music, including contributions to songs recorded by artists like Willie Nelson.
-
C.
Duanne Sutter
Duanne Sutter is a former Canadian professional ice hockey player, best known as one of the Sutter brothers who played in the NHL and won multiple Stanley Cups with the New York Islanders.
-
D.
Michael Nolin
Michael Nolin is an American film producer best known for his work on the acclaimed music drama "Mr. Holland's Opus."
-
E.
Andy Jurgensen
Andy Jurgensen is a film editor known for his work on acclaimed movies such as Licorice Pizza.
- 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_69d7bdf92b588190acdf2a2291ac4590 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d9719d4d1c8190a2c4f362e1772a73 |
completed | April 10, 2026, 9:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6d5ef4ba8819099335d155feb01d9 |
completed | May 3, 2026, 4:58 a.m. |
Created at: April 9, 2026, 5:41 p.m.