Triple

T13037198
Position Surface form Disambiguated ID Type / Status
Subject Tim Howes E326592 entity
Predicate employer P7 FINISHED
Object Opsware E47370 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: Opsware | Statement: [Tim Howes, employer, Opsware]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Opsware
Context triple: [Tim Howes, employer, Opsware]
  • A. Opsware chosen
    Opsware was a data center automation and IT infrastructure management software company, best known for being co-founded by Marc Andreessen and later acquired by Hewlett-Packard.
  • B. Avaya
    Avaya is an American multinational technology company specializing in business communications, unified communications, and contact center solutions for enterprises and organizations worldwide.
  • C. AdventNet Inc.
    AdventNet Inc. was the original name of Zoho Corporation, a software company best known for its suite of online productivity and business applications.
  • D. Agere Systems
    Agere Systems was a semiconductor company specializing in communications and networking integrated circuits, formed as a spin-off from Lucent Technologies.
  • E. Barracuda Networks
    Barracuda Networks is a cybersecurity and data protection company known for providing email security, network security, and backup solutions for businesses.
  • 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_69d8076cc45c81908123123f43e69266 completed April 9, 2026, 8:09 p.m.
NER Named-entity recognition batch_69d97f2a71a0819098bb6cf8a4b2208a completed April 10, 2026, 10:52 p.m.
NED1 Entity disambiguation (via context triple) batch_69f6cbd12eec81908ad5dae638c2210e completed May 3, 2026, 4:15 a.m.
Created at: April 9, 2026, 8:55 p.m.