Triple
T10539745
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | David Wenham |
E248663
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object |
Carl
Carl is a supporting character in the film "Van Helsing," depicted as a witty and inventive friar who aids the titular monster hunter.
|
E870938
|
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: Carl | Statement: [David Wenham, portrayed, Carl]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Carl Context triple: [David Wenham, portrayed, Carl]
-
A.
Carl
Carl is the given name of the 19th-century German mathematician Carl Gustav Jacob Jacobi, renowned for his foundational work in elliptic functions and other areas of mathematics.
-
B.
Carl
Carl is the given name of Nobel Prize–winning physicist Carl E. Wieman, known for his work on Bose–Einstein condensates and physics education research.
-
C.
Carl
Carl is a supporting character in the classic film "Casablanca," working at Rick Blaine's nightclub, Rick's Café Américain.
-
D.
Carl
Carl is the abusive father of Claireece "Precious" Jones in the novel and film "Precious," central to the story's depiction of trauma and hardship.
-
E.
Carl
Carl is the given first name of the renowned Swedish actor Max von Sydow, known for his extensive work in European and Hollywood cinema.
- 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: Carl Triple: [David Wenham, portrayed, Carl]
Generated description
Carl is a supporting character in the film "Van Helsing," depicted as a witty and inventive friar who aids the titular monster hunter.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Carl Target entity description: Carl is a supporting character in the film "Van Helsing," depicted as a witty and inventive friar who aids the titular monster hunter.
-
A.
Carl
Carl is a supporting character in the classic film "Casablanca," working at Rick Blaine's nightclub, Rick's Café Américain.
-
B.
Carl
Carl is a central character in the British comedy film "The Boat That Rocked," portrayed as a young man who joins a pirate radio ship in the 1960s and comes of age amid its rebellious DJs and rock music culture.
-
C.
Carl
Carl is the abusive father of Claireece "Precious" Jones in the novel and film "Precious," central to the story's depiction of trauma and hardship.
-
D.
Carl
Carl is the given first name of the renowned Swedish actor Max von Sydow, known for his extensive work in European and Hollywood cinema.
-
E.
Carl
Carl is the given name of Carl Ferdinand Howard Henry, a prominent American evangelical theologian and author.
- 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_69d381c5c7448190bec34bee7ec72bac |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d50a582be48190856c6f272eea4dcf |
completed | April 7, 2026, 1:44 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d9340da2948190950e7c0ceea12cb1 |
completed | April 10, 2026, 5:31 p.m. |
| NEDg | Description generation | batch_69d93802a4488190aa86ae209650d4e7 |
completed | April 10, 2026, 5:48 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d938fcc3c48190a4acaaf75c1aa304 |
completed | April 10, 2026, 5:53 p.m. |
Created at: April 6, 2026, 12:32 p.m.