Triple
T34124561
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 周平王 |
E875237
|
entity |
| Predicate | 所属文明 |
P25001
|
FINISHED |
| Object | 中华文明 |
—
|
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: 中华文明 | Statement: [周平王, 所属文明, 中华文明]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所属文明 Context triple: [周平王, 所属文明, 中华文明]
-
A.
coreCivilization
Indicates that an entity functions as a central or foundational civilization within a broader cultural, historical, or systemic context.
-
B.
hasCivilization
chosen
Indicates that an entity possesses, hosts, or is associated with an organized society or culture characterized by social, political, and technological development.
-
C.
describesCivilizationType
Indicates that one entity characterizes or specifies the type or category of civilization to which another entity belongs.
-
D.
focusesOnCivilization
Indicates that an entity’s primary subject, concern, or activity is centered on a particular civilization or civilizations.
-
E.
civilization
Indicates that an entity is a civilization, i.e., a complex, organized human society characterized by structured institutions, culture, and social systems.
- 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_69f349aa33848190a2e6c5e4533c8444 |
completed | April 30, 2026, 12:23 p.m. |
| NER | Named-entity recognition | batch_69f70fb4f18c819099ef6d9177b7d205 |
completed | May 3, 2026, 9:04 a.m. |
| PD | Predicate disambiguation | batch_69f70f3a54d481909ba6bdda3647b761 |
completed | May 3, 2026, 9:02 a.m. |
Created at: May 1, 2026, 1:53 a.m.