Triple
T2795362
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Pyongyang |
E53022
|
entity |
| Predicate | hasOperationalGoal |
P43199
|
FINISHED |
| Object | expel Chinese forces from Pyongyang |
—
|
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: expel Chinese forces from Pyongyang | Statement: [Battle of Pyongyang, hasOperationalGoal, expel Chinese forces from Pyongyang]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasOperationalGoal Context triple: [Battle of Pyongyang, hasOperationalGoal, expel Chinese forces from Pyongyang]
-
A.
hasManagementGoal
Indicates that an entity is associated with a specific management objective or target it is intended to achieve or support.
-
B.
hasPrimaryGoal
Indicates that an entity’s main or most important objective is the specified goal.
-
C.
hasPolicyGoal
Indicates that an entity is associated with, or aims to achieve, a specific policy objective or target.
-
D.
strategicGoal
Indicates that one entity represents a long-term objective or desired outcome that another entity is intentionally aiming to achieve or align actions toward.
-
E.
hasGoalYear
Indicates that an entity is associated with a specific target year by which a goal or objective is intended to be achieved.
- 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_69ab495a90788190941b6917e1eca3a6 |
completed | March 6, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69abddef754081908e6218dc2208e0fd |
completed | March 7, 2026, 8:12 a.m. |
| PD | Predicate disambiguation | batch_69abdd040f9481908e9c7a2df88ea1ae |
completed | March 7, 2026, 8:08 a.m. |
| PDg | Predicate description generation | batch_69abddcc348081908b5f760899389d4f |
completed | March 7, 2026, 8:11 a.m. |
Created at: March 6, 2026, 9:58 p.m.