Triple
T21446926
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Requiem for a Nun |
E529101
|
entity |
| Predicate | followsWork |
P9710
|
FINISHED |
| Object | Sanctuary |
—
|
NE NERFINISHED |
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: Sanctuary | Statement: [Requiem for a Nun, followsWork, Sanctuary]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sanctuary Context triple: [Requiem for a Nun, followsWork, Sanctuary]
-
A.
Sanctuary
chosen
Sanctuary is a dark, controversial novel by William Faulkner that explores violence, corruption, and moral decay in the American South.
-
B.
Sanctuary
"Sanctuary" is a short story by Harlem Renaissance writer Nella Larsen that explores themes of racial injustice, guilt, and moral ambiguity in the Jim Crow South.
-
C.
Sanctuary
Sanctuary is a science fiction-fantasy television series known for its use of green screen technology and visual effects, in which Christopher Heyerdahl played multiple prominent roles.
-
D.
Sanctuary
Sanctuary is the mortal realm in the Diablo universe, a world created by angels and demons as a refuge from their eternal war.
-
E.
Sanctuary
"Sanctuary" is a jazz fusion composition by the Mahavishnu Orchestra, featured on their 1973 album *Birds of Fire*.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e0c457579481909db68053ed99750c |
completed | April 16, 2026, 11:13 a.m. |
| NER | Named-entity recognition | batch_69e9e9cea7bc81909ee3e1cdeda1fe7e |
completed | April 23, 2026, 9:43 a.m. |
Created at: April 16, 2026, 6:06 p.m.