Triple
T4060375
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 颐和园 |
E86196
|
entity |
| Predicate | 所属河流系统 |
P1009
|
FINISHED |
| Object | 玉泉山水系 |
—
|
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: 玉泉山水系 | Statement: [颐和园, 所属河流系统, 玉泉山水系]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: 所属河流系统 Context triple: [颐和园, 所属河流系统, 玉泉山水系]
-
A.
tributarySystem
Indicates a relationship where one political entity pays regular tribute or offers deference to another, acknowledging the latter’s superior authority or status.
-
B.
hasMajorRiverSystem
Indicates that an entity possesses or is traversed by a primary, large-scale river network that significantly characterizes its hydrology or geography.
-
C.
riverSystem
chosen
Indicates that one entity is a river system to which the other entity belongs or is a component (such as a tributary or segment).
-
D.
isOneOfLongestRiverSystemsIn
Indicates that a river system ranks among the longest river systems within the specified geographic region or set.
-
E.
waterwaySystem
Indicates that one entity is part of, or belongs to, a connected network of waterways 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_69aed93c69208190a4efac0efe3cd69b |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aefd0bdea48190805a79515ee92709 |
completed | March 9, 2026, 5:02 p.m. |
| PD | Predicate disambiguation | batch_69aef90438908190a005b08ba271eacf |
completed | March 9, 2026, 4:44 p.m. |
Created at: March 9, 2026, 3:38 p.m.