Triple
T26369043
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Xiaoting |
E660720
|
entity |
| Predicate | impactOnWu |
P102027
|
FINISHED |
| Object | secured western frontier against Shu |
—
|
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: secured western frontier against Shu | Statement: [Battle of Xiaoting, impactOnWu, secured western frontier against Shu]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: impactOnWu Context triple: [Battle of Xiaoting, impactOnWu, secured western frontier against Shu]
-
A.
impactStatus
Indicates the current state or condition of how something has affected or influenced a target.
-
B.
recognizesImpactOn
Indicates that one entity acknowledges or understands the effect or consequences it has on another entity or situation.
-
C.
impactOnSubject
chosen
Indicates the effect, influence, or consequence that one entity, event, or action has on a specified subject.
-
D.
impactOnLeader
Indicates that one entity has an effect, influence, or consequence on a leader within a given context.
-
E.
impactBuilding
Indicates that one entity physically collides with or strikes a building, causing an impact event.
- 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_69ee812a698881908d6a58265995fa39 |
completed | April 26, 2026, 9:18 p.m. |
| NER | Named-entity recognition | batch_69f67257b0448190a13011af81c81449 |
completed | May 2, 2026, 9:53 p.m. |
| PD | Predicate disambiguation | batch_69f66ec3d3d48190ab2f2b71939e572e |
completed | May 2, 2026, 9:38 p.m. |
Created at: April 26, 2026, 10:57 p.m.