Triple
T2644076
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beetlejuice |
E62943
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Adam Maitland
Adam Maitland is a mild-mannered, recently deceased husband who becomes a ghost trying to protect his home in Tim Burton’s dark comedy film "Beetlejuice."
|
E296233
|
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: Adam Maitland | Statement: [Beetlejuice, character, Adam Maitland]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Adam Maitland Context triple: [Beetlejuice, character, Adam Maitland]
-
A.
Ian Mackley
Ian Mackley is the husband of British comedian and television personality Julian Clary.
-
B.
Ian Bryce
Ian Bryce is a British film producer known for his work on major Hollywood blockbusters such as Saving Private Ryan and the Transformers series.
-
C.
Adam Gough
Adam Gough is a British film editor known for his work on acclaimed films such as "Da 5 Bloods" and "Roma."
-
D.
Stephen MacLean
Stephen MacLean was an Australian screenwriter and filmmaker best known for his work on music-infused films and television, including the cult musical comedy "Starstruck" (1982).
-
E.
Andrew Millar
Andrew Millar was an 18th-century Scottish-born London bookseller and publisher known for issuing major works of Enlightenment authors, including David Hume.
- 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: Adam Maitland Triple: [Beetlejuice, character, Adam Maitland]
Generated description
Adam Maitland is a mild-mannered, recently deceased husband who becomes a ghost trying to protect his home in Tim Burton’s dark comedy film "Beetlejuice."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Adam Maitland Target entity description: Adam Maitland is a mild-mannered, recently deceased husband who becomes a ghost trying to protect his home in Tim Burton’s dark comedy film "Beetlejuice."
-
A.
Ian Mackley
Ian Mackley is the husband of British comedian and television personality Julian Clary.
-
B.
Ian Bryce
Ian Bryce is a British film producer known for his work on major Hollywood blockbusters such as Saving Private Ryan and the Transformers series.
-
C.
Adam Gough
Adam Gough is a British film editor known for his work on acclaimed films such as "Da 5 Bloods" and "Roma."
-
D.
Stephen MacLean
Stephen MacLean was an Australian screenwriter and filmmaker best known for his work on music-infused films and television, including the cult musical comedy "Starstruck" (1982).
-
E.
Andrew Millar
Andrew Millar was an 18th-century Scottish-born London bookseller and publisher known for issuing major works of Enlightenment authors, including David Hume.
- 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_69ab4c3f2dcc819082df80f5e032f690 |
completed | March 6, 2026, 9:50 p.m. |
| NER | Named-entity recognition | batch_69abd90046dc81908bab3440733f1e98 |
completed | March 7, 2026, 7:51 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69afc02acc048190812d7d2d8b59058a |
completed | March 10, 2026, 6:54 a.m. |
| NEDg | Description generation | batch_69afc0a3dcb4819098e922989fb8165c |
completed | March 10, 2026, 6:56 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69afc10deaa4819082ad29756b651480 |
completed | March 10, 2026, 6:58 a.m. |
Created at: March 6, 2026, 9:53 p.m.