Triple

T144751
Position Surface form Disambiguated ID Type / Status
Subject Chicago Bears E2929 entity
Predicate homeStadium P890 FINISHED
Object Soldier Field E1663 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: Soldier Field | Statement: [Chicago Bears, homeStadium, Soldier Field]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Soldier Field
Context triple: [Chicago Bears, homeStadium, Soldier Field]
  • A. Soldier Field chosen
    Soldier Field is a historic outdoor stadium in Chicago best known as the longtime home of the NFL’s Chicago Bears and a prominent venue for major sports and entertainment events.
  • B. Lincoln Financial Field
    Lincoln Financial Field is a major outdoor sports stadium in Philadelphia, best known as the home of the NFL’s Philadelphia Eagles.
  • C. SHI Stadium
    SHI Stadium is a college football stadium that serves as the home field for the Rutgers University Scarlet Knights.
  • D. Municipal Grant Park Stadium
    Municipal Grant Park Stadium was the original name of Soldier Field, the historic multi-purpose stadium on Chicago’s lakefront best known as the longtime home of the NFL’s Chicago Bears.
  • E. Reser Stadium
    Reser Stadium is the primary football stadium and home field of the Oregon State Beavers in Corvallis, Oregon.
  • 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_69a2521e35c08190b28e5c9f1e3c9b59 completed Feb. 28, 2026, 2:25 a.m.
NER Named-entity recognition batch_69a257e935bc8190a03e54a10e9ba6f7 completed Feb. 28, 2026, 2:50 a.m.
NED1 Entity disambiguation (via context triple) batch_69a3836d16d081909d8046cf6a10d421 completed March 1, 2026, 12:08 a.m.
Created at: Feb. 28, 2026, 2:31 a.m.