Triple

T18351477
Position Surface form Disambiguated ID Type / Status
Subject Killing Commendatore E439675 entity
Predicate hasCharacter P2308 FINISHED
Object Mariye
Mariye is a perceptive and enigmatic young girl who plays a central, symbolic role in Haruki Murakami’s novel "Killing Commendatore."
E1319690 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: Mariye | Statement: [Killing Commendatore, hasCharacter, Mariye]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mariye
Context triple: [Killing Commendatore, hasCharacter, Mariye]
  • A. Mariamman
    Mariamman is a South Indian Hindu goddess primarily associated with rain, fertility, and the cure of diseases such as smallpox.
  • B. Anoush
    Anoush is a renowned Armenian opera by composer Armen Tigranian, based on Hovhannes Tumanyan’s poem and celebrated for its lyrical portrayal of rural Armenian life and tragic love.
  • C. Zinya
    Zinya is a diminutive, affectionate form of the Russian male given name Zinovy.
  • D. Soraya
    Soraya was an Iranian-German actress and former Queen consort of Iran as the second wife of Shah Mohammad Reza Pahlavi.
  • E. Soraya
    Soraya is the wife of Rashid Khalifa, a member of the Bahraini royal family.
  • 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: Mariye
Triple: [Killing Commendatore, hasCharacter, Mariye]
Generated description
Mariye is a perceptive and enigmatic young girl who plays a central, symbolic role in Haruki Murakami’s novel "Killing Commendatore."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Mariye
Target entity description: Mariye is a perceptive and enigmatic young girl who plays a central, symbolic role in Haruki Murakami’s novel "Killing Commendatore."
  • A. Mariamman
    Mariamman is a South Indian Hindu goddess primarily associated with rain, fertility, and the cure of diseases such as smallpox.
  • B. Anoush
    Anoush is a renowned Armenian opera by composer Armen Tigranian, based on Hovhannes Tumanyan’s poem and celebrated for its lyrical portrayal of rural Armenian life and tragic love.
  • C. Zinya
    Zinya is a diminutive, affectionate form of the Russian male given name Zinovy.
  • D. Soraya
    Soraya was an Iranian-German actress and former Queen consort of Iran as the second wife of Shah Mohammad Reza Pahlavi.
  • E. Soraya
    Soraya is the wife of Rashid Khalifa, a member of the Bahraini royal family.
  • 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_69d8b918221c8190a9f7b563d64ac677 completed April 10, 2026, 8:47 a.m.
NER Named-entity recognition batch_69e514f83b648190b473cf611851c666 completed April 19, 2026, 5:46 p.m.
NED1 Entity disambiguation (via context triple) batch_6a03cc28b80c8190819b989478bb62bd completed May 13, 2026, 12:56 a.m.
NEDg Description generation batch_6a03cd1858c481909f78fb1a4c27437c completed May 13, 2026, 1 a.m.
NED2 Entity disambiguation (via description) batch_6a03ce9e3dd08190b912fe9e9f552053 completed May 13, 2026, 1:06 a.m.
Created at: April 10, 2026, 10:37 a.m.