Triple
T17305269
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Patrick Marber |
E420143
|
entity |
| Predicate | wroteScreenplay |
P15305
|
FINISHED |
| Object | Asylum |
E749700
|
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: Asylum | Statement: [Patrick Marber, wroteScreenplay, Asylum]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Asylum Context triple: [Patrick Marber, wroteScreenplay, Asylum]
-
A.
Asylum
"Asylum" is a soulful R&B track by John Legend from his album *Love in the Future*, blending emotive vocals with lush, contemporary production.
-
B.
Asylum
chosen
"Asylum" is a 2005 psychological drama film, based on Patrick McGrath’s novel, about a psychiatrist’s wife who begins a dangerous affair with a patient at a British mental institution.
-
C.
Asylum
Asylum is a record label known for signing influential rock and singer-songwriter artists, particularly in the 1970s.
-
D.
Asylum
Asylum is a heavy metal album by the American band Disturbed, noted for its dark themes and powerful, aggressive sound.
-
E.
Chasing Asylum
Chasing Asylum is a documentary film that exposes and critiques Australia’s offshore detention policies for asylum seekers.
- 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_69d889d22b848190a4663d0b8f8f76e7 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e438fe1d408190a429d1dba50d0c58 |
completed | April 19, 2026, 2:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0180de8340819081eae1104d705de0 |
completed | May 11, 2026, 7:10 a.m. |
Created at: April 10, 2026, 5:43 a.m.