Triple
T7049487
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | How to Steal a Million |
E163727
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Simon Dermott
Simon Dermott is the charming, clever art expert and thief portrayed by Peter O’Toole in the 1966 heist comedy film "How to Steal a Million."
|
E639393
|
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: Simon Dermott | Statement: [How to Steal a Million, mainCharacter, Simon Dermott]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Simon Dermott Context triple: [How to Steal a Million, mainCharacter, Simon Dermott]
-
A.
David DeMott
David DeMott is an American entrepreneur best known as one of the founders behind the creation of the SeaWorld marine theme park concept.
-
B.
Phil Jordan
Phil Jordan is a musician best known as a former member of the American rock band No Doubt.
-
C.
Sean Whalen
Sean Whalen is an American character actor known for his distinctive, often quirky roles in film and television, including horror and cult favorites.
-
D.
Matthew Richardson
Matthew Richardson is a former Australian rules footballer widely regarded as one of Richmond Football Club’s greatest forwards and a fan favourite in the AFL.
-
E.
Kevin Stoney
Kevin Stoney was a British character actor best known for his villainous roles in classic science fiction television, particularly in series like Doctor Who.
- 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: Simon Dermott Triple: [How to Steal a Million, mainCharacter, Simon Dermott]
Generated description
Simon Dermott is the charming, clever art expert and thief portrayed by Peter O’Toole in the 1966 heist comedy film "How to Steal a Million."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Simon Dermott Target entity description: Simon Dermott is the charming, clever art expert and thief portrayed by Peter O’Toole in the 1966 heist comedy film "How to Steal a Million."
-
A.
David DeMott
David DeMott is an American entrepreneur best known as one of the founders behind the creation of the SeaWorld marine theme park concept.
-
B.
Phil Jordan
Phil Jordan is a musician best known as a former member of the American rock band No Doubt.
-
C.
Sean Whalen
Sean Whalen is an American character actor known for his distinctive, often quirky roles in film and television, including horror and cult favorites.
-
D.
Matthew Richardson
Matthew Richardson is a former Australian rules footballer widely regarded as one of Richmond Football Club’s greatest forwards and a fan favourite in the AFL.
-
E.
Kevin Stoney
Kevin Stoney was a British character actor best known for his villainous roles in classic science fiction television, particularly in series like Doctor Who.
- 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_69c6885f598c8190b6b6495c59d8d962 |
completed | March 27, 2026, 1:38 p.m. |
| NER | Named-entity recognition | batch_69c6e24d5e8c8190b37e56107e6da8ab |
completed | March 27, 2026, 8:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c7888bba9c8190b6414b56e5588ec0 |
completed | March 28, 2026, 7:51 a.m. |
| NEDg | Description generation | batch_69c788f292a08190bf3543ecfc245d12 |
completed | March 28, 2026, 7:53 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c789a6ea988190ad2db2442f0a5e8f |
completed | March 28, 2026, 7:56 a.m. |
Created at: March 27, 2026, 2:37 p.m.