Triple
T11983575
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Barbara Maitland |
E285218
|
entity |
| Predicate | enemy |
P4567
|
FINISHED |
| Object | Charles Deetz |
E403992
|
NE FINISHED |
How this triple was built (2 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: Charles Deetz | Statement: [Barbara Maitland, enemy, Charles Deetz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Charles Deetz Context triple: [Barbara Maitland, enemy, Charles Deetz]
-
A.
Charles Deetz
chosen
Charles Deetz is a nervous, real-estate-obsessed father who moves his family into a haunted country house in the dark comedy film "Beetlejuice."
-
B.
Charles Leickert
Charles Leickert was a 19th-century Dutch painter renowned for his atmospheric winter landscapes and cityscapes of the Netherlands.
-
C.
Charles Bohl
Charles Bohl is a screenwriter best known for his work on the 2002 psychological thriller film "Swimfan."
-
D.
Charles Rettig
Charles Rettig is an American tax attorney who served as the Commissioner of the Internal Revenue Service (IRS) from 2018 to 2022.
-
E.
John Dinkeloo
John Dinkeloo was an American architect best known for his partnership with Eero Saarinen and later leadership of Kevin Roche John Dinkeloo and Associates, contributing to numerous influential modernist buildings.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69d6ab44a77c8190a652f4b27164e4ef |
completed | April 8, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69d903973c848190aac871d6dfecc74b |
completed | April 10, 2026, 2:05 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f74602a7ec8190980e5e6a80aa1235 |
completed | May 3, 2026, 12:56 p.m. |
Created at: April 8, 2026, 9:46 p.m.