Triple

T19027179
Position Surface form Disambiguated ID Type / Status
Subject Tinius Trust E465638 entity
Predicate namedAfter P63 FINISHED
Object Tinius Nagell-Erichsen
Tinius Nagell-Erichsen was a Norwegian publisher and media executive best known for his leadership role in the Schibsted media group and his commitment to independent journalism.
 E465638 NE FINISHED

How this triple was built (4 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: Tinius Nagell-Erichsen | Statement: [Tinius Trust, namedAfter, Tinius Nagell-Erichsen]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tinius Nagell-Erichsen
Context triple: [Tinius Trust, namedAfter, Tinius Nagell-Erichsen]
  • A. Tinius Trust
    Tinius Trust is a Norwegian foundation that safeguards the long-term, independent ownership and editorial freedom of media group Schibsted.
  • B. Lammeter
    Lammeter is the surname of Nancy Lammeter, a character in George Eliot’s novel "Silas Marner."
  • C. Micronite
    Micronite is a brand of cigarette filter historically associated with Kent cigarettes, known for its controversial use of asbestos in early filter designs.
  • D. Nicolson
    Nicolson is a surname that serves as a spelling variant of the more common family name Nicholson.
  • E. Leister
    Leister is a surname of English origin borne by various individuals, including those with the given name Edward.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Tinius Nagell-Erichsen
Triple: [Tinius Trust, namedAfter, Tinius Nagell-Erichsen]
Generated description
Tinius Nagell-Erichsen was a Norwegian publisher and media executive best known for his leadership role in the Schibsted media group and his commitment to independent journalism.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tinius Nagell-Erichsen
Target entity description: Tinius Nagell-Erichsen was a Norwegian publisher and media executive best known for his leadership role in the Schibsted media group and his commitment to independent journalism.
  • A. Tinius Trust chosen
    Tinius Trust is a Norwegian foundation that safeguards the long-term, independent ownership and editorial freedom of media group Schibsted.
  • B. Lammeter
    Lammeter is the surname of Nancy Lammeter, a character in George Eliot’s novel "Silas Marner."
  • C. Micronite
    Micronite is a brand of cigarette filter historically associated with Kent cigarettes, known for its controversial use of asbestos in early filter designs.
  • D. Nicolson
    Nicolson is a surname that serves as a spelling variant of the more common family name Nicholson.
  • E. Leister
    Leister is a surname of English origin borne by various individuals, including those with the given name Edward.
  • F. None of above.

Provenance (5 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_69d8dd0359648190bc2a9202c5cf29d2 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5d73dc404819092059e496662d151 completed April 20, 2026, 7:35 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05be5811e88190aae947755f554492 completed May 14, 2026, 12:21 p.m.
NEDg Description generation batch_6a05bf6819b08190851561a489f66d3f completed May 14, 2026, 12:26 p.m.
NED2 Entity disambiguation (via description) batch_6a05bfe2ab5c8190a969f060b01ee913 completed May 14, 2026, 12:28 p.m.
Created at: April 10, 2026, 12:02 p.m.