Triple
T433892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Leonardo DiCaprio |
E9770
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object |
Dom Cobb
Dom Cobb is the skilled professional thief and extractor who leads dream-infiltration heists in Christopher Nolan's science-fiction film "Inception."
|
E54681
|
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: Dom Cobb | Statement: [Leonardo DiCaprio, portrayed, Dom Cobb]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Dom Cobb Context triple: [Leonardo DiCaprio, portrayed, Dom Cobb]
-
A.
John Kenway
John Kenway is a cinematographer best known for his work on the acclaimed 1995 television adaptation of Jane Austen's "Pride and Prejudice."
-
B.
Jason Bourne
Jason Bourne is a fictional amnesiac assassin and highly skilled operative at the center of Robert Ludlum’s spy novels and the popular action-thriller film series.
-
C.
Ray
Ray is a masculine given name commonly used in English-speaking countries, often as a short form of Raymond.
-
D.
Kyle Reese
Kyle Reese is a time-traveling resistance fighter from the Terminator franchise, best known as John Connor’s father and protector of Sarah Connor against Skynet’s machines.
-
E.
Roland Caulder
Roland Caulder is an actor known for his role in the film "The Iron Mask."
- 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: Dom Cobb Triple: [Leonardo DiCaprio, portrayed, Dom Cobb]
Generated description
Dom Cobb is the skilled professional thief and extractor who leads dream-infiltration heists in Christopher Nolan's science-fiction film "Inception."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Dom Cobb Target entity description: Dom Cobb is the skilled professional thief and extractor who leads dream-infiltration heists in Christopher Nolan's science-fiction film "Inception."
-
A.
John Kenway
John Kenway is a cinematographer best known for his work on the acclaimed 1995 television adaptation of Jane Austen's "Pride and Prejudice."
-
B.
Jason Bourne
Jason Bourne is a fictional amnesiac assassin and highly skilled operative at the center of Robert Ludlum’s spy novels and the popular action-thriller film series.
-
C.
Ray
Ray is a masculine given name commonly used in English-speaking countries, often as a short form of Raymond.
-
D.
Kyle Reese
Kyle Reese is a time-traveling resistance fighter from the Terminator franchise, best known as John Connor’s father and protector of Sarah Connor against Skynet’s machines.
-
E.
Roland Caulder
Roland Caulder is an actor known for his role in the film "The Iron Mask."
- 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_69a2e801e1d48190b505d1dd336b52ac |
completed | Feb. 28, 2026, 1:05 p.m. |
| NER | Named-entity recognition | batch_69a2ef0a008c8190ae0aa25e4df9c35f |
completed | Feb. 28, 2026, 1:35 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a431e541108190b0d7f3f34f7b32c7 |
completed | March 1, 2026, 12:32 p.m. |
| NEDg | Description generation | batch_69a4325f970c8190b2c64b39321b6d6f |
completed | March 1, 2026, 12:34 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69a433663f608190a09c4e600bf53a57 |
completed | March 1, 2026, 12:39 p.m. |
Created at: Feb. 28, 2026, 1:11 p.m.