Triple

T20060750
Position Surface form Disambiguated ID Type / Status
Subject Thom Barry E499464 entity
Predicate notableWork P4 FINISHED
Object 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: Steel | Statement: [Thom Barry, notableWork, Steel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Steel
Context triple: [Thom Barry, notableWork, Steel]
  • A. Steel
    Steel is a Scottish Liberal Democrat politician who served as leader of the Liberal Party and was the first Presiding Officer of the Scottish Parliament.
  • B. Steel chosen
    Steel is a 1997 superhero film based on the DC Comics character John Henry "Steel" Irons, featuring Shaquille O'Neal in the title role.
  • C. Steel
    Steel is a strong, durable alloy primarily composed of iron and carbon, widely used in construction, manufacturing, and tools.
  • D. Cor-Ten steel
    Cor-Ten steel is a high-strength, low-alloy weathering steel known for forming a stable, rust-like protective patina that eliminates the need for painting and is widely used in architecture and outdoor structures.
  • E. Damascene steel
    Damascene steel is a famed historical type of patterned, high-carbon steel renowned for its exceptional strength, sharpness, and distinctive wavy surface designs used in swords and blades.
  • 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_69da6276bcf48190aabbf279192a5fb4 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e6637601dc8190a07fc20844093cb7 completed April 20, 2026, 5:33 p.m.
Created at: April 11, 2026, 3:38 p.m.