Triple

T634978
Position Surface form Disambiguated ID Type / Status
Subject AT&T Stadium E16603 entity
Predicate architect P184 FINISHED
Object HKS, Inc. E8834 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: HKS, Inc. | Statement: [AT&T Stadium, architect, HKS, Inc.]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: HKS, Inc.
Context triple: [AT&T Stadium, architect, HKS, Inc.]
  • A. HKS, Inc. chosen
    HKS, Inc. is a global architecture firm known for designing major sports, entertainment, and commercial venues.
  • B. HKS
    HKS is the Harvard Kennedy School, a leading public policy and public administration graduate school at Harvard University.
  • C. HOK Group
    HOK Group is a global design, architecture, engineering, and planning firm known for large-scale commercial, civic, and sports projects.
  • D. RTKL Associates Inc.
    RTKL Associates Inc. is a global architecture and design firm known for large-scale civic, commercial, and mixed-use projects.
  • E. HGA Architects and Engineers
    HGA Architects and Engineers is a multidisciplinary American design firm known for its architectural and engineering work on major civic and cultural projects, including the U.S. Capitol Visitor Center.
  • 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_69a4936be1c88190af56540324b57da7 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49ee4ee8481908ad45405e3f3835c completed March 1, 2026, 8:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69a57405d6f48190b55542d50d3a1f22 completed March 2, 2026, 11:27 a.m.
Created at: March 1, 2026, 7:35 p.m.