Triple
T17674746
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spec# |
E440617
|
entity |
| Predicate | developer |
P73
|
FINISHED |
| Object |
Mike Barnett
Mike Barnett is a software developer associated with the Spec# programming language and verification project.
|
E1346591
|
NE FINISHED |
How this triple was built (4 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: Mike Barnett | Statement: [Spec#, developer, Mike Barnett]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mike Barnett Context triple: [Spec#, developer, Mike Barnett]
-
A.
Brian Bockrath
Brian Bockrath is a television producer best known for his executive production work on the post-apocalyptic horror drama series The Walking Dead: Dead City.
-
B.
Brian Routh
Brian Routh was a British performance artist and musician best known as one half of the avant-garde comedy and performance duo The Kipper Kids.
-
C.
Mike Bennion
Mike Bennion is a musician best known for having been an early member of the British progressive rock band Porcupine Tree.
-
D.
Keith Batey
Keith Batey was a British codebreaker and intelligence officer who worked at Bletchley Park during World War II, notably alongside his wife, fellow cryptanalyst Mavis Batey.
-
E.
Kevin Barnett
Kevin Barnett was an American comedian and screenwriter known for co-writing mainstream comedy films and working on various television and stand-up projects.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mike Barnett Triple: [Spec#, developer, Mike Barnett]
Generated description
Mike Barnett is a software developer associated with the Spec# programming language and verification project.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mike Barnett Target entity description: Mike Barnett is a software developer associated with the Spec# programming language and verification project.
-
A.
Brian Bockrath
Brian Bockrath is a television producer best known for his executive production work on the post-apocalyptic horror drama series The Walking Dead: Dead City.
-
B.
Brian Routh
Brian Routh was a British performance artist and musician best known as one half of the avant-garde comedy and performance duo The Kipper Kids.
-
C.
Mike Bennion
Mike Bennion is a musician best known for having been an early member of the British progressive rock band Porcupine Tree.
-
D.
Keith Batey
Keith Batey was a British codebreaker and intelligence officer who worked at Bletchley Park during World War II, notably alongside his wife, fellow cryptanalyst Mavis Batey.
-
E.
Kevin Barnett
Kevin Barnett was an American comedian and screenwriter known for co-writing mainstream comedy films and working on various television and stand-up projects.
- F. None of above. chosen
Provenance (5 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_69d8b9e87e18819087104a44dc4dc5b1 |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e46f6ba22081909e2099490c047378 |
completed | April 19, 2026, 6 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a05759c98248190a7483912ae13b425 |
completed | May 14, 2026, 7:11 a.m. |
| NEDg | Description generation | batch_6a057718c3b48190813b5bc51f75405c |
completed | May 14, 2026, 7:17 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a05777f51b481909a7916bc40dcfd69 |
completed | May 14, 2026, 7:19 a.m. |
Created at: April 10, 2026, 10 a.m.