Triple
T21439841
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | High Life |
E528908
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Geoff Cox
Geoff Cox is a screenwriter best known for his work on the film "High Life."
|
E1484426
|
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: Geoff Cox | Statement: [High Life, screenwriter, Geoff Cox]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Geoff Cox Context triple: [High Life, screenwriter, Geoff Cox]
-
A.
Geoff Tootill
Geoff Tootill was a British electronic engineer and computer scientist who helped build some of the world’s earliest stored-program computers.
-
B.
Geoff Bell
Geoff Bell is a British character actor known for his tough-guy roles in films such as "Green Street," "The Business," and "Kingsman: The Secret Service."
-
C.
Geoff Walters
Geoff Walters is a central fictional news anchor character in the Australian television drama series "The Newsreader."
-
D.
Colin Blakely
Colin Blakely was a Northern Irish character actor known for his powerful stage work and memorable supporting roles in British and international films of the 1960s–1980s.
-
E.
Brett Ewins
Brett Ewins was a British comic book artist best known for his influential work on 2000 AD titles like Judge Dredd and Rogue Trooper, as well as co-creating the comic magazine Deadline.
- 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: Geoff Cox Triple: [High Life, screenwriter, Geoff Cox]
Generated description
Geoff Cox is a screenwriter best known for his work on the film "High Life."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Geoff Cox Target entity description: Geoff Cox is a screenwriter best known for his work on the film "High Life."
-
A.
Geoff Tootill
Geoff Tootill was a British electronic engineer and computer scientist who helped build some of the world’s earliest stored-program computers.
-
B.
Geoff Bell
Geoff Bell is a British character actor known for his tough-guy roles in films such as "Green Street," "The Business," and "Kingsman: The Secret Service."
-
C.
Geoff Walters
Geoff Walters is a central fictional news anchor character in the Australian television drama series "The Newsreader."
-
D.
Colin Blakely
Colin Blakely was a Northern Irish character actor known for his powerful stage work and memorable supporting roles in British and international films of the 1960s–1980s.
-
E.
Brett Ewins
Brett Ewins was a British comic book artist best known for his influential work on 2000 AD titles like Judge Dredd and Rogue Trooper, as well as co-creating the comic magazine Deadline.
- 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_69e0c4569fa081908101baa24f8745db |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e8b700237c8190bbcb4bedc4242719 |
completed | April 22, 2026, 11:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a09c8ff456481908092ae0af1297aab |
completed | May 17, 2026, 1:56 p.m. |
| NEDg | Description generation | batch_6a09c99200a88190ad13565044dfcac0 |
completed | May 17, 2026, 1:58 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a09ca3c4ec48190829b1bd83b933f53 |
completed | May 17, 2026, 2:01 p.m. |
Created at: April 16, 2026, 6:05 p.m.