Triple
T31850123
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zhou royal house |
E813042
|
entity |
| Predicate | legitimizingDoctrine |
P129811
|
FINISHED |
| Object | Mandate of Heaven |
—
|
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: Mandate of Heaven | Statement: [Zhou royal house, legitimizingDoctrine, Mandate of Heaven]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: legitimizingDoctrine Context triple: [Zhou royal house, legitimizingDoctrine, Mandate of Heaven]
-
A.
religiousLegitimation
chosen
Indicates that something is justified, authorized, or validated by reference to religious beliefs, doctrines, or institutions.
-
B.
doctrineOf
Indicates a relationship where one entity is the doctrinal teaching, principle, or belief system associated with, derived from, or formally held by another entity.
-
C.
clarifiedDoctrineOn
Indicates that one entity has provided a more precise, authoritative, or detailed explanation of a doctrine concerning another entity.
-
D.
primaryDoctrine
Indicates that the object represents the main or foundational doctrine associated with the subject.
-
E.
doctrinalDomain
Indicates the specific area of doctrine or body of teachings within which a belief, statement, or rule is classified.
- 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_69f348eb327881909b4584b925742f6e |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69f6b03b97608190885c36d98edf0afb |
completed | May 3, 2026, 2:17 a.m. |
| PD | Predicate disambiguation | batch_69f6aca59d4881908d14ed47962703bd |
completed | May 3, 2026, 2:02 a.m. |
Created at: April 30, 2026, 11:51 p.m.