Triple

T24395711
Position Surface form Disambiguated ID Type / Status
Subject Battle for Sevastopol E615021 entity
Predicate editor P1954 FINISHED
Object Maria Sergeenkova
Maria Sergeenkova is a film editor known for her work on the World War II biographical drama "Battle for Sevastopol."
E1727808 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: Maria Sergeenkova | Statement: [Battle for Sevastopol, editor, Maria Sergeenkova]
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: Maria Sergeenkova
Triple: [Battle for Sevastopol, editor, Maria Sergeenkova]
Generated description
Maria Sergeenkova is a film editor known for her work on the World War II biographical drama "Battle for Sevastopol."

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_69e2d7e509b88190a53155d4f3de45ce completed April 18, 2026, 1:01 a.m.
NER Named-entity recognition batch_69f294d69b5c81908cf6143374934f5c completed April 29, 2026, 11:31 p.m.
NED1 Entity disambiguation (via context triple) batch_6a11bae82160819093fff05fb2544a27 completed May 23, 2026, 2:34 p.m.
NEDg Description generation batch_6a11be5eaa64819093fca394daf91d90 completed May 23, 2026, 2:49 p.m.
NED2 Entity disambiguation (via description) batch_6a11bf1dd27c8190b77577de860ac016 completed May 23, 2026, 2:52 p.m.
Created at: April 18, 2026, 2:04 a.m.