Triple

T14821256
Position Surface form Disambiguated ID Type / Status
Subject Mark Strand E348457 entity
Predicate birthName P65 FINISHED
Object Mark Strand E348457 NE FINISHED

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: Mark Strand | Statement: [Mark Strand, birthName, Mark Strand]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mark Strand
Context triple: [Mark Strand, birthName, Mark Strand]
  • A. Mark Strand chosen
    Mark Strand was a Pulitzer Prize–winning Canadian-born American poet, essayist, and translator known for his spare, meditative verse and for serving as U.S. Poet Laureate.
  • B. Stephen Dunn
    Stephen Dunn was an American poet and Pulitzer Prize winner known for his accessible, reflective verse exploring everyday life and human relationships.
  • C. Doug Mahon
    Doug Mahon is a technology entrepreneur best known as a founder of the data storage company Seagate Technology.
  • D. C. K. Williams
    C. K. Williams was an American poet renowned for his long-lined, morally probing verse and major awards including the Pulitzer Prize and National Book Award.
  • E. Galway Kinnell
    Galway Kinnell was an American poet known for his emotionally intense, nature-infused verse and his association with the confessional and deep image poetry movements.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69d822eb8f588190bf53445e730a934f completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69decfe64328819083ce42704cf0602d completed April 14, 2026, 11:38 p.m.
NED1 Entity disambiguation (via context triple) batch_69feae005644819098937cedb53202c5 completed May 9, 2026, 3:46 a.m.
Created at: April 10, 2026, 1:50 a.m.