Triple
T492895
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Creed (film) |
E10226
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Tony Bellew
Tony Bellew is a British former professional boxer who became widely known beyond the sport for playing the antagonist "Pretty" Ricky Conlan in the film Creed.
|
E61813
|
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: Tony Bellew | Statement: [Creed (film), starring, Tony Bellew]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tony Bellew Context triple: [Creed (film), starring, Tony Bellew]
-
A.
Stephen Smith
Stephen Smith is a member of the Smith family, known as the son of Benjamin A. Smith II.
-
B.
Cameron Bairstow
Cameron Bairstow is an Australian professional basketball player and former New Mexico Lobos standout who briefly played in the NBA with the Chicago Bulls.
-
C.
Daniel Jones
Daniel Jones was a British phonetician and linguist renowned for codifying and popularizing the model of Received Pronunciation in English.
-
D.
Andy King
Andy King is one of the sons of the late American television and radio host Larry King.
-
E.
Will Firth
Will Firth is the son of English actor Colin Firth and is known primarily for his connection to his father's prominent film career.
- 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: Tony Bellew Triple: [Creed (film), starring, Tony Bellew]
Generated description
Tony Bellew is a British former professional boxer who became widely known beyond the sport for playing the antagonist "Pretty" Ricky Conlan in the film Creed.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tony Bellew Target entity description: Tony Bellew is a British former professional boxer who became widely known beyond the sport for playing the antagonist "Pretty" Ricky Conlan in the film Creed.
-
A.
Stephen Smith
Stephen Smith is a member of the Smith family, known as the son of Benjamin A. Smith II.
-
B.
Cameron Bairstow
Cameron Bairstow is an Australian professional basketball player and former New Mexico Lobos standout who briefly played in the NBA with the Chicago Bulls.
-
C.
Daniel Jones
Daniel Jones was a British phonetician and linguist renowned for codifying and popularizing the model of Received Pronunciation in English.
-
D.
Andy King
Andy King is one of the sons of the late American television and radio host Larry King.
-
E.
Will Firth
Will Firth is the son of English actor Colin Firth and is known primarily for his connection to his father's prominent film career.
- 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_69a2e847df8481909239ec08ccf1e376 |
completed | Feb. 28, 2026, 1:06 p.m. |
| NER | Named-entity recognition | batch_69a2f0faab4881909f65f172198b5bd2 |
completed | Feb. 28, 2026, 1:43 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a47d2c33bc81909d0743ca3ef96c00 |
completed | March 1, 2026, 5:53 p.m. |
| NEDg | Description generation | batch_69a480d0d5608190b9adf3bc9803e765 |
completed | March 1, 2026, 6:09 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a4811bb2fc81909f524d172f7ba9b7 |
completed | March 1, 2026, 6:10 p.m. |
Created at: Feb. 28, 2026, 1:12 p.m.