Triple

T15418119
Position Surface form Disambiguated ID Type / Status
Subject Martha Helen Kostyra E369303 entity
Predicate familyName P18 FINISHED
Object Kostyra
Kostyra is the birth surname of American businesswoman and media personality Martha Stewart (born Martha Helen Kostyra).
E1156706 NE FINISHED

How this triple was built (4 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: Kostyra | Statement: [Martha Helen Kostyra, familyName, Kostyra]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kostyra
Context triple: [Martha Helen Kostyra, familyName, Kostyra]
  • A. Stary Krym
    Stary Krym is a historic town in eastern Crimea known for its medieval heritage and role as an important center in the Crimean Peninsula’s past.
  • B. Orlovika
    Orlovika is an alternative name for the Orlov Revolt, an 18th-century Greek uprising against Ottoman rule encouraged by Russia during the Russo-Turkish War.
  • C. Obskaya
    Obskaya is a settlement and railway station in Russia’s Yamalo-Nenets Autonomous Okrug that serves as a key junction for rail transport into the Yamal Peninsula.
  • D. Nedomanský
    Nedomanský is a Czech surname most notably associated with Václav Nedomanský, a prominent former professional ice hockey player and Hall of Famer.
  • E. Derazhnia
    Derazhnia is a small town in western Ukraine known as a local administrative and transportation center within the Khmelnytskyi region.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
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: Kostyra
Triple: [Martha Helen Kostyra, familyName, Kostyra]
Generated description
Kostyra is the birth surname of American businesswoman and media personality Martha Stewart (born Martha Helen Kostyra).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kostyra
Target entity description: Kostyra is the birth surname of American businesswoman and media personality Martha Stewart (born Martha Helen Kostyra).
  • A. Stary Krym
    Stary Krym is a historic town in eastern Crimea known for its medieval heritage and role as an important center in the Crimean Peninsula’s past.
  • B. Orlovika
    Orlovika is an alternative name for the Orlov Revolt, an 18th-century Greek uprising against Ottoman rule encouraged by Russia during the Russo-Turkish War.
  • C. Obskaya
    Obskaya is a settlement and railway station in Russia’s Yamalo-Nenets Autonomous Okrug that serves as a key junction for rail transport into the Yamal Peninsula.
  • D. Nedomanský
    Nedomanský is a Czech surname most notably associated with Václav Nedomanský, a prominent former professional ice hockey player and Hall of Famer.
  • E. Derazhnia
    Derazhnia is a small town in western Ukraine known as a local administrative and transportation center within the Khmelnytskyi region.
  • F. None of above. chosen

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_69d85a1849f48190bf898068b2806fae completed April 10, 2026, 2:02 a.m.
NER Named-entity recognition batch_69e03ebce4f48190ba282ecb4fb2f6fa completed April 16, 2026, 1:43 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff1a78f9cc819097a6ff1e0cbdbcf3 completed May 9, 2026, 11:28 a.m.
NEDg Description generation batch_69ff1bc3aa2c8190b61d21fa78682ea1 completed May 9, 2026, 11:34 a.m.
NED2 Entity disambiguation (via description) batch_69ff1cbccab48190b9e19b5a09324d8c completed May 9, 2026, 11:38 a.m.
Created at: April 10, 2026, 3:20 a.m.