Triple
T15625312
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Safety Not Guaranteed |
E375662
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object | Derek Connolly |
E269776
|
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: Derek Connolly | Statement: [Safety Not Guaranteed, screenwriter, Derek Connolly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Derek Connolly Context triple: [Safety Not Guaranteed, screenwriter, Derek Connolly]
-
A.
Derek Connolly
chosen
Derek Connolly is an American screenwriter best known for co-writing major science fiction and adventure films such as Jurassic World and its sequels.
-
B.
Ryan Connolly
Ryan Connolly is a filmmaker and YouTube personality best known for creating the popular filmmaking education channel Film Riot.
-
C.
Derek Corrigan
Derek Corrigan is a Canadian politician who served for many years as the mayor of Burnaby, British Columbia, known for his strong stances on urban development and environmental issues.
-
D.
Ken Connell
Ken Connell is a Marvel Comics character who becomes the human wielder of the immensely powerful cosmic artifact known as the Star Brand.
-
E.
Chris Connolly
Chris Connolly is a personal name shared by multiple individuals, including professionals in fields such as sports, media, and the arts.
- 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_69d85cd035a48190b73d5579ab73969a |
completed | April 10, 2026, 2:13 a.m. |
| NER | Named-entity recognition | batch_69e04e9e5e248190ae54cda1fde51efb |
completed | April 16, 2026, 2:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff82e73534819095fca1b804d5db58 |
completed | May 9, 2026, 6:54 p.m. |
Created at: April 10, 2026, 4:14 a.m.