Triple
T22794413
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saviors |
E564203
|
entity |
| Predicate | baseOfOperations |
P2591
|
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: [Saviors, baseOfOperations, Sanctuary]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sanctuary Context triple: [Saviors, baseOfOperations, Sanctuary]
-
A.
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.
-
B.
Sanctuary
chosen
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.
-
C.
Sanctuary
Sanctuary is the mortal realm in the Diablo universe, a world created by angels and demons as a refuge from their eternal war.
-
D.
Sanctuary
"Sanctuary" is an album by the experimental rock band Praying Mantis, showcasing their distinctive blend of melodic and progressive elements.
-
E.
Sanctuary
Sanctuary is a dark, controversial novel by William Faulkner that explores violence, corruption, and moral decay in the American South.
- 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_69e2458185f88190b0045227ee420411 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17cd81794819091b528600e322d7b |
completed | April 29, 2026, 3:36 a.m. |
Created at: April 17, 2026, 3:30 p.m.