Triple
T28374306
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 成湯 |
E718714
|
entity |
| Predicate | 被視為 |
P1120
|
FINISHED |
| Object | 有德之君 |
—
|
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: 有德之君 | Statement: [成湯, 被視為, 有德之君]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 被視為 Context triple: [成湯, 被視為, 有德之君]
-
A.
considered
chosen
Indicates that one entity regards, judges, or thinks about another entity in a particular way or context.
-
B.
canBeViewedAs
Indicates that one entity may be interpreted, treated, or understood as another entity or type under some perspective or conditions.
-
C.
consideredIn
Indicates that one entity is taken into account, examined, or included as a factor within the context, scope, or decision framework of another entity.
-
D.
viewedBySomeAs
Indicates that at least one observer or group perceives or interprets an entity in a particular way or role.
-
E.
treatsAsSubject
Indicates that one entity regards, handles, or processes another entity in the role or capacity of a subject (e.g., topic, focus, or primary object of consideration).
- 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_69eff6ee5afc8190bd7375a29f0cc6c6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_69f64c5d1290819087cbb832239699d4 |
completed | May 2, 2026, 7:11 p.m. |
| PD | Predicate disambiguation | batch_69f641e2f1708190b45b48d6a43c51d2 |
completed | May 2, 2026, 6:26 p.m. |
Created at: April 28, 2026, 1:02 a.m.