Triple

T22499440
Position Surface form Disambiguated ID Type / Status
Subject Brent Mydland E556228 entity
Predicate notableWork P4 FINISHED
Object “Tons of Steel” 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: “Tons of Steel” | Statement: [Brent Mydland, notableWork, “Tons of Steel”]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: “Tons of Steel”
Context triple: [Brent Mydland, notableWork, “Tons of Steel”]
  • A. Tons of Steel chosen
    Tons of Steel is a song featured on the Grateful Dead’s album "In the Dark."
  • B. Cast in Steel
    Cast in Steel is a 2015 studio album by Norwegian synth-pop band A-ha that marked their return after a brief split, blending nostalgic sounds with contemporary production.
  • C. Made of Steel
    Made of Steel is a Doctor Who tie-in novel featuring the Tenth Doctor, written for younger readers as part of the Quick Reads initiative.
  • D. Smoke and Steel
    Smoke and Steel is a 1920 poetry collection by American writer Carl Sandburg that explores industrialization, urban life, and the American working class in a free-verse, modernist style.
  • E. Street of Steel
    Street of Steel is a prominent thoroughfare in King’s Landing in the world of *A Song of Ice and Fire*, known for its many smithies and metalworkers.
  • 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_69e11e5445bc8190b6a9481926db3355 completed April 16, 2026, 5:37 p.m.
NER Named-entity recognition batch_69f15cb4ff8c8190af0c60abafefe832 completed April 29, 2026, 1:19 a.m.
Created at: April 16, 2026, 8:50 p.m.