Triple

T10339333
Position Surface form Disambiguated ID Type / Status
Subject Mardik Martin E243087 entity
Predicate givenName P17 FINISHED
Object Mardik
Mardik is the given name of Mardik Martin, an American screenwriter known for his collaborations with director Martin Scorsese.
 E858205 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: Mardik | Statement: [Mardik Martin, givenName, Mardik]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mardik
Context triple: [Mardik Martin, givenName, Mardik]
  • A. Mardian
    Mardian is a minor eunuch and servant in William Shakespeare’s tragedy "Antony and Cleopatra," known for his loyalty to Cleopatra.
  • B. Vostanik
    Vostanik is the birth name of Arshile Gorky, the influential Armenian-American painter associated with Abstract Expressionism.
  • C. Mardaric
    Mardaric is a minor river in southeastern France that serves as one of the tributaries feeding the Bléone River.
  • D. Murjan
    Murjan was a concubine in the Umayyad court of Córdoba and the mother of the Caliph Al-Hakam II.
  • E. Martunashen
    Martunashen is a village in the disputed Nagorno-Karabakh region, known for being one of the sites affected by the Soviet Azerbaijani security forces’ Operation Ring in 1991.
  • 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: Mardik
Triple: [Mardik Martin, givenName, Mardik]
Generated description
Mardik is the given name of Mardik Martin, an American screenwriter known for his collaborations with director Martin Scorsese.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mardik
Target entity description: Mardik is the given name of Mardik Martin, an American screenwriter known for his collaborations with director Martin Scorsese.
  • A. Mardian
    Mardian is a minor eunuch and servant in William Shakespeare’s tragedy "Antony and Cleopatra," known for his loyalty to Cleopatra.
  • B. Vostanik
    Vostanik is the birth name of Arshile Gorky, the influential Armenian-American painter associated with Abstract Expressionism.
  • C. Mardaric
    Mardaric is a minor river in southeastern France that serves as one of the tributaries feeding the Bléone River.
  • D. Murjan
    Murjan was a concubine in the Umayyad court of Córdoba and the mother of the Caliph Al-Hakam II.
  • E. Martunashen
    Martunashen is a village in the disputed Nagorno-Karabakh region, known for being one of the sites affected by the Soviet Azerbaijani security forces’ Operation Ring in 1991.
  • 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_69d381af787481908bc401325c760a88 completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4e0a470948190959f298dd6110bf3 completed April 7, 2026, 10:47 a.m.
NED1 Entity disambiguation (via context triple) batch_69d7506a07888190b91e78247e81fe57 completed April 9, 2026, 7:08 a.m.
NEDg Description generation batch_69d7618c9abc819080c4d6669dfb8320 completed April 9, 2026, 8:21 a.m.
NED2 Entity disambiguation (via description) batch_69d7702ae24481908b0f5319413e81d4 completed April 9, 2026, 9:23 a.m.
Created at: April 6, 2026, 11:54 a.m.