Triple
T26369038
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Xiaoting |
E660720
|
entity |
| Predicate | ShuForces |
P160462
|
FINISHED |
| Object | large invasion army led personally by Liu Bei |
—
|
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: large invasion army led personally by Liu Bei | Statement: [Battle of Xiaoting, ShuForces, large invasion army led personally by Liu Bei]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: ShuForces Context triple: [Battle of Xiaoting, ShuForces, large invasion army led personally by Liu Bei]
-
A.
ChineseCommander
Indicates that an individual holds a commander role within a Chinese military or armed forces context.
-
B.
ChineseForcesType
Indicates a relationship where a specified force or military unit is classified as belonging to Chinese forces or military types.
-
C.
ChineseForcesStrength
Indicates the level or magnitude of military strength or capability possessed by Chinese forces in a given context.
-
D.
usesForces
Indicates that one entity applies physical, magical, or other types of forces to influence, move, or affect another entity.
-
E.
SpanishForceComponent
Indicates that an entity functions as a component or sub-unit of a Spanish military or armed force.
- F. None of above. chosen
Provenance (4 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_69f6102dfc848190a94d1ef0f3c9e04e |
completed | May 2, 2026, 2:54 p.m. |
| PD | Predicate disambiguation | batch_69f5f800fa9c8190aab0962669fde8ac |
completed | May 2, 2026, 1:11 p.m. |
| PDg | Predicate description generation | batch_69f6018ceb1c8190a6a5f84071659a96 |
completed | May 2, 2026, 1:52 p.m. |
Created at: April 26, 2026, 10:57 p.m.