Triple
T30639096
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sun Quan–Liu Bei alliance |
E779924
|
entity |
| Predicate | formedToCounter |
P39773
|
FINISHED |
| Object | Cao Cao’s southward campaign |
—
|
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: Cao Cao’s southward campaign | Statement: [Sun Quan–Liu Bei alliance, formedToCounter, Cao Cao’s southward campaign]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: formedToCounter Context triple: [Sun Quan–Liu Bei alliance, formedToCounter, Cao Cao’s southward campaign]
-
A.
formedTo
chosen
Indicates that one entity was created, established, or organized for the purpose of serving, supporting, or enabling another entity or activity.
-
B.
formedWithin
Indicates that one entity was created, established, or came into existence inside the spatial or structural bounds of another entity.
-
C.
formedState
Indicates that an entity brought a particular state, condition, or configuration into existence or caused it to come about.
-
D.
madeTo
Indicates that one entity is created, produced, or constructed for the purpose, use, or benefit of another entity.
-
E.
constructedTo
Indicates that one entity has been built, created, or designed for the purpose of serving, supporting, or enabling 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_69f224a50ebc81909b961a94c7f66b12 |
completed | April 29, 2026, 3:32 p.m. |
| NER | Named-entity recognition | batch_69fefb15220081908da36aac386fa582 |
completed | May 9, 2026, 9:15 a.m. |
| PD | Predicate disambiguation | batch_69fefa8e8ad48190a723fed81e9d64d0 |
completed | May 9, 2026, 9:12 a.m. |
Created at: April 29, 2026, 8:29 p.m.