Triple
T3955318
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Marston |
E84962
|
entity |
| Predicate | createdBy |
P806
|
FINISHED |
| Object |
Michael Unsworth
Michael Unsworth is a video game writer best known for his work on Rockstar Games titles such as the Red Dead Redemption series.
|
E405402
|
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: Michael Unsworth | Statement: [John Marston, createdBy, Michael Unsworth]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Unsworth Context triple: [John Marston, createdBy, Michael Unsworth]
-
A.
David Hartnett
David Hartnett is a British civil servant best known for serving as the Permanent Secretary for Tax at HM Revenue and Customs, where he was the UK's top tax official.
-
B.
Gareth Unwin
Gareth Unwin is a British film producer best known for his Academy Award-winning work on the historical drama "The King’s Speech."
-
C.
Phil Woolpert
Phil Woolpert was a prominent American college basketball coach best known for leading the University of San Francisco to multiple national championships in the 1950s.
-
D.
Paul Wilson
Paul Wilson is a Scottish musician best known as the bassist for the alternative rock band Snow Patrol.
-
E.
Graham Carr
Graham Carr is a Canadian academic and administrator who serves as the president of Concordia University in Montreal.
- 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: Michael Unsworth Triple: [John Marston, createdBy, Michael Unsworth]
Generated description
Michael Unsworth is a video game writer best known for his work on Rockstar Games titles such as the Red Dead Redemption series.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michael Unsworth Target entity description: Michael Unsworth is a video game writer best known for his work on Rockstar Games titles such as the Red Dead Redemption series.
-
A.
David Hartnett
David Hartnett is a British civil servant best known for serving as the Permanent Secretary for Tax at HM Revenue and Customs, where he was the UK's top tax official.
-
B.
Gareth Unwin
Gareth Unwin is a British film producer best known for his Academy Award-winning work on the historical drama "The King’s Speech."
-
C.
Phil Woolpert
Phil Woolpert was a prominent American college basketball coach best known for leading the University of San Francisco to multiple national championships in the 1950s.
-
D.
Paul Wilson
Paul Wilson is a Scottish musician best known as the bassist for the alternative rock band Snow Patrol.
-
E.
Graham Carr
Graham Carr is a Canadian academic and administrator who serves as the president of Concordia University in Montreal.
- 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_69aed934fbfc8190847068e4546de963 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef93f3ad48190b96b98b4aecd6030 |
completed | March 9, 2026, 4:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b54c3de4688190b0eeb2604a65803e |
completed | March 14, 2026, 11:53 a.m. |
| NEDg | Description generation | batch_69b54cafe41c8190aa294333e24f2d5f |
completed | March 14, 2026, 11:55 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b54ce20be081908296da47e4ee9fc0 |
completed | March 14, 2026, 11:56 a.m. |
Created at: March 9, 2026, 3:30 p.m.