Triple
T30119563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Guangshun |
E765520
|
entity |
| Predicate | eraScope |
P29664
|
FINISHED |
| Object | imperial Chinese calendar system |
—
|
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: imperial Chinese calendar system | Statement: [Guangshun, eraScope, imperial Chinese calendar system]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: eraScope Context triple: [Guangshun, eraScope, imperial Chinese calendar system]
-
A.
isoScope
Indicates that one entity defines or constrains the scope or boundary within which another entity is considered equivalent or comparable.
-
B.
canBeSeenWith
Indicates that two entities are observable together in the same context, setting, or time.
-
C.
eraSystem
chosen
Indicates a temporal classification relationship where an entity is associated with a particular era or chronological system used to organize time.
-
D.
hasSpectrograph
Indicates that one entity is equipped with or contains a spectrograph instrument.
-
E.
oreControl
Indicates a relationship where one entity exercises authority or regulatory control over the extraction, management, or use of ore resources associated with another entity.
- F. None of above.
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_69f2247716748190ae4f16998f49ddf1 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69f67dea016c8190b961a805960152bb |
completed | May 2, 2026, 10:42 p.m. |
| PD | Predicate disambiguation | batch_69f673c664f08190b4d66cdc305e10db |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 29, 2026, 7:13 p.m.