Triple
T32182568
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Shusha 1826 |
E822024
|
entity |
| Predicate | defenseOf |
P6876
|
FINISHED |
| Object | Shusha fortress |
—
|
NE NERFINISHED |
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: Shusha fortress | Statement: [Siege of Shusha 1826, defenseOf, Shusha fortress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defenseOf Context triple: [Siege of Shusha 1826, defenseOf, Shusha fortress]
-
A.
defends
chosen
Indicates that one entity protects or supports another entity against attack, criticism, or harm.
-
B.
defendedAs
Indicates that one entity is presented, argued, or justified as being equivalent to or serving the role of another entity in a defensive or protective context.
-
C.
defenseArgument
Indicates that an entity presents or supports a line of reasoning intended to defend or justify another entity, often in a legal or argumentative context.
-
D.
defendedOn
Indicates that one entity protected, supported, or argued in favor of another entity during a specific time or event.
-
E.
defenseResult
Indicates the outcome or consequence of a defensive action or strategy in response to an attack or threat.
- 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_69f3490755288190aee11740a34862f9 |
completed | April 30, 2026, 12:20 p.m. |
| NER | Named-entity recognition | batch_69f7431c0eec81909ead443e07d75e18 |
completed | May 3, 2026, 12:44 p.m. |
| PD | Predicate disambiguation | batch_69f74143cf708190a12d487884298437 |
completed | May 3, 2026, 12:36 p.m. |
Created at: May 1, 2026, 12:34 a.m.