Triple

T28345086
Position Surface form Disambiguated ID Type / Status
Subject Black Sea Cossack Host E717926 entity
Predicate notableCenter P16715 FINISHED
Object Ekaterinodar fortress
Ekaterinodar fortress was a key military stronghold and administrative hub of the Black Sea Cossacks in the North Caucasus region of the Russian Empire.
E1816032 NE 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: Ekaterinodar fortress | Statement: [Black Sea Cossack Host, notableCenter, Ekaterinodar fortress]
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Ekaterinodar fortress
Triple: [Black Sea Cossack Host, notableCenter, Ekaterinodar fortress]
Generated description
Ekaterinodar fortress was a key military stronghold and administrative hub of the Black Sea Cossacks in the North Caucasus region of the Russian Empire.

Provenance (5 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_69eff6eb30388190b898b96c4be6f49d completed April 27, 2026, 11:53 p.m.
NER Named-entity recognition batch_69f64c063b448190a572f5a7049c4070 completed May 2, 2026, 7:09 p.m.
NED1 Entity disambiguation (via context triple) batch_6a1632f89c7c8190b6b10eec594c2c00 completed May 26, 2026, 11:55 p.m.
NEDg Description generation batch_6a163527b4348190860c7ee809601573 completed May 27, 2026, 12:04 a.m.
NED2 Entity disambiguation (via description) batch_6a1635a5a5508190ba0353c33d03edaa completed May 27, 2026, 12:07 a.m.
Created at: April 28, 2026, 12:42 a.m.