Triple

T6122657
Position Surface form Disambiguated ID Type / Status
Subject Thunderbird E136519 entity
Predicate supportsAuthentication P203 FINISHED
Object NTLM E196384 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: NTLM | Statement: [Thunderbird, supportsAuthentication, NTLM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: NTLM
Context triple: [Thunderbird, supportsAuthentication, NTLM]
  • A. NTLM chosen
    NTLM is a Microsoft authentication protocol used to validate users and secure access in Windows-based networks and services.
  • B. Kerberos
    Kerberos is a small, irregularly shaped moon of Pluto discovered in 2011 as part of the Pluto system’s complex family of satellites.
  • C. Kerberos
    Kerberos is a network authentication protocol that uses secret-key cryptography to securely verify the identity of users and services in distributed systems.
  • D. NTL
    NTL was a major UK cable television and telecommunications company that became part of Virgin Media following a series of mergers and rebrandings.
  • E. NTLs
    NTLs are formal regulatory documents issued to inform lessees and operators of updated requirements, guidelines, or procedures governing their activities.
  • 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_69c0089f851c81909e5e189a617dcff6 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c05c247b7081909972b40afb165e6f completed March 22, 2026, 9:16 p.m.
NED1 Entity disambiguation (via context triple) batch_69c135abcef08190a899d7ba261ebb04 completed March 23, 2026, 12:44 p.m.
Created at: March 22, 2026, 4:14 p.m.