Triple

T17802905
Position Surface form Disambiguated ID Type / Status
Subject Scott Scherr E444477 entity
Predicate employer P7 FINISHED
Object Ultimate Software 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: Ultimate Software | Statement: [Scott Scherr, employer, Ultimate Software]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Ultimate Software
Context triple: [Scott Scherr, employer, Ultimate Software]
  • A. Ultimate Software chosen
    Ultimate Software was a leading American provider of cloud-based human capital management and payroll software solutions for businesses.
  • B. Appirio
    Appirio is a cloud services and consulting company known for helping enterprises implement and optimize platforms like Salesforce and Workday.
  • C. Deltek
    Deltek is a software company specializing in enterprise resource planning and project-based solutions for government contractors and professional services firms.
  • D. Atria Software
    Atria Software was a software company best known for creating the ClearCase configuration management and version control system later acquired by Rational Software.
  • E. Procore Technologies
    Procore Technologies is a construction management software company that provides cloud-based tools to help construction professionals manage projects, resources, and collaboration.
  • 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_69d8b9efe370819095cd219b143ae727 completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e4880171608190be2088c7a387bfb7 completed April 19, 2026, 7:45 a.m.
Created at: April 10, 2026, 10:13 a.m.