Triple
T19648324
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Take Back the Night |
E471738
|
entity |
| Predicate | musicVideoDirector |
P4911
|
FINISHED |
| Object | Jonathan Craven |
—
|
NE NERFINISHED |
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: Jonathan Craven | Statement: [Take Back the Night, musicVideoDirector, Jonathan Craven]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jonathan Craven Context triple: [Take Back the Night, musicVideoDirector, Jonathan Craven]
-
A.
Jonathan Craven
chosen
Jonathan Craven is a music video director and filmmaker known for his work on various rock and alternative music projects, as well as being the son of horror director Wes Craven.
-
B.
Nicholas Crane
Nicholas Crane is a British geographer, author, and television presenter known for his work on geography-themed documentaries and popular science books.
-
C.
Ian Masters
Ian Masters is a screenwriter best known for his work on the political thriller film "The Osterman Weekend."
-
D.
Peter Craven
Peter Craven is a co-founder of the Australian literary and cultural magazine MQA.
-
E.
Michael Ripper
Michael Ripper was a British character actor best known for his prolific supporting roles in Hammer horror films from the 1950s to the 1970s.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69d8e51395348190ac1416d46dfc6db0 |
completed | April 10, 2026, 11:54 a.m. |
| NER | Named-entity recognition | batch_69e64126cea88190a1a6929f46de4686 |
completed | April 20, 2026, 3:07 p.m. |
Created at: April 10, 2026, 1:44 p.m.