Triple
T10202023
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Doom (2005 film) |
E238904
|
entity |
| Predicate | editedBy |
P1954
|
FINISHED |
| Object | Derek Brechin |
E598481
|
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 Brechin | Statement: [Doom (2005 film), editedBy, Derek Brechin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Derek Brechin Context triple: [Doom (2005 film), editedBy, Derek Brechin]
-
A.
Derek Brechin
chosen
Derek Brechin is a film editor best known for his work on the action movie "Romeo Must Die."
-
B.
Martin Dougan
Martin Dougan is a Scottish television presenter and former wheelchair basketball player best known for his work on the BBC children's news programme Newsround.
-
C.
Jay Beattie
Jay Beattie is a television writer and producer best known for his work on genre series, including serving as a developer of the horror TV continuation of the Scream franchise.
-
D.
Scott Devine
Scott Devine is a technology entrepreneur best known as one of the co-founders of VMware, a pioneering company in virtualization and cloud computing.
-
E.
Ian Ritchie
Ian Ritchie is a British architect known for his innovative, high-tech designs and for leading the practice Ian Ritchie Architects.
- 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_69ca84e1ea088190b38162e43d4cfa8f |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cdee4239c08190b40f5cc19c3db3c7 |
completed | April 2, 2026, 4:19 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d71c68d0cc8190994c4b0aaaf7829a |
completed | April 9, 2026, 3:26 a.m. |
Created at: March 30, 2026, 9:14 p.m.