Triple

T22025596
Position Surface form Disambiguated ID Type / Status
Subject Ali ibn Musa E543952 entity
Predicate residence P75 FINISHED
Object Marv NE NERFINISHED

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: Marv | Statement: [Ali ibn Musa, residence, Marv]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Marv
Context triple: [Ali ibn Musa, residence, Marv]
  • A. Marv chosen
    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 Won
    Marv Won is a Detroit-based underground hip-hop artist and producer known for his sharp lyricism and battle rap pedigree.
  • D. Marvin
    Marvin is the given first name of Pro Football Hall of Fame coach Marv Levy, known for leading the Buffalo Bills to four consecutive Super Bowl appearances.
  • E. Marvin
    Marvin is the given first name of the renowned American playwright and screenwriter Neil Simon.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69e11e2e8ea4819084210fe06d3a1b8d completed April 16, 2026, 5:36 p.m.
NER Named-entity recognition batch_69f127cba61c8190a48ec2c1ee1315b0 completed April 28, 2026, 9:34 p.m.
Created at: April 16, 2026, 8:24 p.m.