Triple

T15328758
Position Surface form Disambiguated ID Type / Status
Subject Layers E366478 entity
Predicate featuresArtist P1952 FINISHED
Object Marv Won
Marv Won is a Detroit-based underground hip-hop artist and producer known for his sharp lyricism and battle rap pedigree.
E1150351 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: Marv Won | Statement: [Layers, featuresArtist, Marv Won]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marv Won
Context triple: [Layers, featuresArtist, Marv Won]
  • A. Marv
    Marv is an ancient city in present-day Turkmenistan that was a major Silk Road hub and one of the great cultural and commercial centers of the Islamic world.
  • B. Marv
    Marv is a masculine given name, often used as a shortened form of Marvin.
  • C. Marv Tarplin
    Marv Tarplin was an American guitarist and songwriter best known for crafting the signature guitar riffs and co-writing many of the classic hits of Smokey Robinson & The Miracles.
  • D. Marv Rich
    Marv Rich was a civil rights activist best known for helping establish the Congress of Racial Equality, a key organization in the U.S. civil rights movement.
  • E. Marv Murchins
    Marv Murchins is one of the bumbling burglar duo known as the "Wet Bandits" in the comedy film *Home Alone*.
  • 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: Marv Won
Triple: [Layers, featuresArtist, Marv Won]
Generated description
Marv Won is a Detroit-based underground hip-hop artist and producer known for his sharp lyricism and battle rap pedigree.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Marv Won
Target entity description: Marv Won is a Detroit-based underground hip-hop artist and producer known for his sharp lyricism and battle rap pedigree.
  • A. Marv
    Marv is an ancient city in present-day Turkmenistan that was a major Silk Road hub and one of the great cultural and commercial centers of the Islamic world.
  • B. Marv
    Marv is a masculine given name, often used as a shortened form of Marvin.
  • C. Marv Tarplin
    Marv Tarplin was an American guitarist and songwriter best known for crafting the signature guitar riffs and co-writing many of the classic hits of Smokey Robinson & The Miracles.
  • D. Marv Rich
    Marv Rich was a civil rights activist best known for helping establish the Congress of Racial Equality, a key organization in the U.S. civil rights movement.
  • E. Marv Murchins
    Marv Murchins is one of the bumbling burglar duo known as the "Wet Bandits" in the comedy film *Home Alone*.
  • 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_69d85a121520819093dcce999fdefe1a completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03dffd6f88190a0f031ee90c6a7d2 completed April 16, 2026, 1:40 a.m.
NED1 Entity disambiguation (via context triple) batch_69fef8af92a88190bd47f1a484f25eb1 completed May 9, 2026, 9:04 a.m.
NEDg Description generation batch_69fefd14736481908cf6b75b74a80f0f completed May 9, 2026, 9:23 a.m.
NED2 Entity disambiguation (via description) batch_69fefd887b6c8190a9ac41a7eadf94f1 completed May 9, 2026, 9:25 a.m.
Created at: April 10, 2026, 3:16 a.m.