Triple
T31873825
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Derbent Khanate |
E813682
|
entity |
| Predicate | hasCapitalFortress |
P25570
|
FINISHED |
| Object | Derbent 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: Derbent fortress | Statement: [Derbent Khanate, hasCapitalFortress, Derbent fortress]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasCapitalFortress Context triple: [Derbent Khanate, hasCapitalFortress, Derbent fortress]
-
A.
hasHistoricCapitolBuilding
Indicates that an entity possesses or is associated with a building that historically served as a capitol or seat of government.
-
B.
wasCitadelOf
chosen
Indicates that a place previously served as the main fortified stronghold or central defensive structure for another entity.
-
C.
hasCityWallsFrom
Indicates that a city’s defensive walls originate from, or were constructed starting at, a specified source location or structure.
-
D.
fortressLocatedOn
Indicates that a fortress is situated on or atop a specified geographic feature, structure, or location.
-
E.
hasMunicipalPalaceIn
Indicates that a municipality possesses or is associated with a municipal palace located in the specified place.
- 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_69f348ecb07481909c8f72619131b115 |
completed | April 30, 2026, 12:19 p.m. |
| NER | Named-entity recognition | batch_69feabcda59481908f2bc13b46fcced1 |
completed | May 9, 2026, 3:36 a.m. |
| PD | Predicate disambiguation | batch_69feaabd63f88190b30dcf6dd2ea39d1 |
completed | May 9, 2026, 3:32 a.m. |
Created at: April 30, 2026, 11:55 p.m.