Triple
T22921469
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kubla Khan (character) |
E568872
|
entity |
| Predicate | associatedWithPlace |
P2830
|
FINISHED |
| Object | Xanadu |
—
|
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: Xanadu | Statement: [Kubla Khan (character), associatedWithPlace, Xanadu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Xanadu Context triple: [Kubla Khan (character), associatedWithPlace, Xanadu]
-
A.
Xanadu
chosen
Xanadu is the opulent, mythical pleasure-dome city evoked in Samuel Taylor Coleridge’s poem "Kubla Khan."
-
B.
Xanadu
Xanadu is a 1980 fantasy musical film blending roller disco, romance, and pop music, starring Olivia Newton-John and featuring songs by Electric Light Orchestra.
-
C.
XANADU
XANADU is the radio callsign used by the long-haul low-cost airline AirAsia X.
-
D.
XANADU
XANADU is a software package within the HEASoft suite used for the analysis and modeling of X-ray and gamma-ray astronomical data.
-
E.
Shangri La
Shangri La is a historic oceanfront estate in Honolulu, Hawaii, best known for its extensive collection of Islamic art and architecture, originally built as the home of philanthropist Doris Duke.
- 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_69e2458d90c88190a58cead4e781ca6a |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f180d5658c81908dbbb5882fcc1b8b |
completed | April 29, 2026, 3:53 a.m. |
Created at: April 17, 2026, 3:43 p.m.