Triple

T23157078
Position Surface form Disambiguated ID Type / Status
Subject Stephen Harriman Long E578471 entity
Predicate designed P184 FINISHED
Object Long truss 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: Long truss | Statement: [Stephen Harriman Long, designed, Long truss]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Long truss
Context triple: [Stephen Harriman Long, designed, Long truss]
  • A. Truss
    Truss is a British Conservative politician who briefly served as Prime Minister of the United Kingdom in 2022.
  • B. Parker truss
    A Parker truss is a type of truss bridge characterized by a polygonal top chord that efficiently distributes loads over longer spans.
  • C. Howe truss chosen
    The Howe truss is a structural bridge and roof truss design characterized by vertical iron or steel tension rods and diagonal wooden compression members, widely used in 19th-century railroad and covered bridges.
  • D. S5 truss segment
    The S5 truss segment is a structural component of the International Space Station’s integrated truss assembly that extends the station’s power and cooling infrastructure.
  • E. Trammel
    Trammel is a notable police officer serving in the Charming Police Department, recognized for his role in law enforcement within the fictional town of Charming.
  • 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_69e245fb8de081908f0eba7b5fd75bc4 completed April 17, 2026, 2:38 p.m.
NER Named-entity recognition batch_69f18efe1b0081908e81b757d64c067c completed April 29, 2026, 4:54 a.m.
Created at: April 17, 2026, 4:01 p.m.