Triple
T14589796
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Andijan uprising of 1898 |
E342412
|
entity |
| Predicate | hasPrimaryOppressor |
P68850
|
FINISHED |
| Object | Tsarist colonial administration |
—
|
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: Tsarist colonial administration | Statement: [Andijan uprising of 1898, hasPrimaryOppressor, Tsarist colonial administration]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPrimaryOppressor Context triple: [Andijan uprising of 1898, hasPrimaryOppressor, Tsarist colonial administration]
-
A.
hasPrimary
Indicates that one entity is designated as the main or most important instance (the primary) in relation to another entity.
-
B.
hasMainAdversary
chosen
Indicates that an entity’s primary or most significant opponent, rival, or enemy is another specified entity.
-
C.
hasPrimaryCharacter
Indicates that an entity features another entity as its main or central character.
-
D.
isVictimOf
Indicates that one entity suffers harm, loss, or wrongdoing as a result of another entity’s actions or events.
-
E.
hasOpposingSide
Indicates that one entity possesses or is associated with another entity that lies on the opposite or facing side relative to a reference orientation or boundary.
- 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_69d822ddc0f081909cd8163c7de298cd |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb4237d88819097f3f9a40f5be152 |
completed | April 14, 2026, 9:39 p.m. |
| PD | Predicate disambiguation | batch_69de656a953481909a4645b004c40de7 |
completed | April 14, 2026, 4:03 p.m. |
Created at: April 10, 2026, 1:24 a.m.