Triple
T10302025
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 2nd Far Eastern Front |
E241653
|
entity |
| Predicate | operationDirection |
P9946
|
FINISHED |
| Object | from the east toward Harbin and Qiqihar |
—
|
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: from the east toward Harbin and Qiqihar | Statement: [2nd Far Eastern Front, operationDirection, from the east toward Harbin and Qiqihar]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: operationDirection Context triple: [2nd Far Eastern Front, operationDirection, from the east toward Harbin and Qiqihar]
-
A.
directionalOperation
chosen
Indicates an operation whose effect depends on or is applied along a specific direction or orientation between entities.
-
B.
offsetDirection
Indicates the relative direction in which one entity is displaced or shifted from another reference entity.
-
C.
containsDirectionOf
Indicates that one entity includes or encompasses the directional orientation or path associated with another entity.
-
D.
operationType
Indicates the specific kind of operation or action being performed or recorded in the relationship between entities.
-
E.
connectionDirection
Indicates the directional flow or orientation of a connection from one entity to another.
- 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_69d381aaafc08190af475ef58dc16aba |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4d30716d8819085e25a78e6af3b9d |
completed | April 7, 2026, 9:48 a.m. |
| PD | Predicate disambiguation | batch_69d4d1f35e548190be3b4d92d65d2d20 |
completed | April 7, 2026, 9:44 a.m. |
Created at: April 6, 2026, 11:45 a.m.