Triple
T12340139
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marvellous |
E294200
|
entity |
| Predicate | portrays |
P264
|
FINISHED |
| Object | Neil Baldwin |
E977915
|
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: Neil Baldwin | Statement: [Marvellous, portrays, Neil Baldwin]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Neil Baldwin Context triple: [Marvellous, portrays, Neil Baldwin]
-
A.
Neil Baldwin
chosen
Neil Baldwin is an English former circus clown and kit man for Stoke City FC whose life story of optimism and resilience inspired the BAFTA-winning film "Marvellous."
-
B.
Duncan Henderson
Duncan Henderson was an American film producer and production manager known for his work on major Hollywood films including "Master and Commander: The Far Side of the World."
-
C.
Mahe Drysdale
Mahe Drysdale is a New Zealand rower renowned for his multiple Olympic and World Championship titles in the single sculls.
-
D.
Daniel Peacock
Daniel Peacock is a British actor, director, and writer known for his work in film and television comedies since the 1980s.
-
E.
Bryan Elsley
Bryan Elsley is a Scottish television writer and producer best known for co-creating the groundbreaking British teen drama series "Skins."
- 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_69d6ab6ccbec8190b09e2d357aa80064 |
completed | April 8, 2026, 7:24 p.m. |
| NER | Named-entity recognition | batch_69d93f7758dc8190bbc6a9ad00b01dce |
completed | April 10, 2026, 6:20 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63ef164508190bc311a8199cfbc70 |
completed | May 2, 2026, 6:14 p.m. |
Created at: April 8, 2026, 9:53 p.m.