Triple

T29432117
Position Surface form Disambiguated ID Type / Status
Subject Seldon Vault E746458 entity
Predicate concealment P177563 FINISHED
Object hidden location on Terminus LITERAL 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: hidden location on Terminus | Statement: [Seldon Vault, concealment, hidden location on Terminus]
PD Predicate disambiguation gpt-5-mini-2025-08-07
Target predicate: concealment
Context triple: [Seldon Vault, concealment, hidden location on Terminus]
  • A. concealmentType
    Indicates the specific manner or method by which something is hidden, obscured, or kept from detection.
  • B. concealability
    Indicates the degree to which something can be hidden or kept from being noticed or discovered.
  • C. riskConcealment
    Indicates that one party hides, downplays, or fails to disclose potential dangers, losses, or adverse outcomes associated with something to another party.
  • D. secretive
    Indicates that an entity deliberately withholds information or conceals its thoughts, actions, or intentions from others.
  • E. triesToConcealCrimeFrom
    Indicates an attempt by one entity to hide, obscure, or prevent another entity from discovering or becoming aware of a crime.
  • F. None of above. chosen

Provenance (4 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_69f0a7a06e0081908add494075912eb4 completed April 28, 2026, 12:27 p.m.
NER Named-entity recognition batch_69f7009d39508190af7301f824615e88 completed May 3, 2026, 8 a.m.
PD Predicate disambiguation batch_69f6fc53f4f881908dcc698687bbb64d completed May 3, 2026, 7:42 a.m.
PDg Predicate description generation batch_69f6ffb7554881908993d6d2ffbcf8f5 completed May 3, 2026, 7:56 a.m.
Created at: April 28, 2026, 3:14 p.m.