Triple
T22118016
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | St Andrew’s Cathedral |
E546589
|
entity |
| Predicate | hostsServiceInLanguage |
P147053
|
FINISHED |
| Object | Mandarin |
—
|
LITERAL 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: Mandarin | Statement: [St Andrew’s Cathedral, hostsServiceInLanguage, Mandarin]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hostsServiceInLanguage Context triple: [St Andrew’s Cathedral, hostsServiceInLanguage, Mandarin]
-
A.
hostsCompany
Indicates that one entity provides space, infrastructure, or support for a company to operate, be located, or hold activities.
-
B.
hostRepublic
Indicates that an entity serves as the host country or republic for another entity or event.
-
C.
hostLatticeFor
Indicates that one entity serves as the structural lattice framework within which another entity is incorporated, embedded, or accommodated.
-
D.
hostEmpire
Indicates that one entity serves as the imperial authority or ruling empire that hosts, controls, or encompasses another entity.
-
E.
hostsAward
Indicates that an entity organizes and presents an award event or ceremony for another entity.
- F. None of above. chosen
Provenance (4 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_69e11e38b3848190ac3a4fa97d56e65a |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1294fcf2c81909b610e03a0f1921f |
completed | April 28, 2026, 9:40 p.m. |
| PD | Predicate disambiguation | batch_69e71b2ed7348190b6fa2e52f54393fb |
completed | April 21, 2026, 6:37 a.m. |
| PDg | Predicate description generation | batch_69e7222d208c819098b12c13e31af629 |
completed | April 21, 2026, 7:07 a.m. |
Created at: April 16, 2026, 8:31 p.m.