Triple

T6021044
Position Surface form Disambiguated ID Type / Status
Subject Bjørn Arild Gram E134063 entity
Predicate familyName P18 FINISHED
Object Gram
Gram is a surname of Scandinavian origin borne by various notable individuals, including Norwegian politician Bjørn Arild Gram.
 E560853 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: Gram | Statement: [Bjørn Arild Gram, familyName, Gram]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Gram
Context triple: [Bjørn Arild Gram, familyName, Gram]
  • A. Grammatiko
    Grammatiko is a village in the East Attica region of Greece, known for its traditional character and proximity to the Marathon area.
  • B. Gramatiko
    Gramatiko is the grammar section of the Fundamento de Esperanto, outlining the core grammatical rules of the Esperanto language.
  • C. .kg
    .kg is the country code top-level domain (ccTLD) assigned to Kyrgyzstan for use in internet addresses.
  • D. Gros
    Gros is a French surname most famously borne by Antoine-Jean Gros, a prominent Napoleonic-era painter known for his dramatic historical and battle scenes.
  • E. Gradelle
    Gradelle is a residential neighborhood within the municipality of Chêne-Bougeries in the canton of Geneva, Switzerland.
  • 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: Gram
Triple: [Bjørn Arild Gram, familyName, Gram]
Generated description
Gram is a surname of Scandinavian origin borne by various notable individuals, including Norwegian politician Bjørn Arild Gram.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Gram
Target entity description: Gram is a surname of Scandinavian origin borne by various notable individuals, including Norwegian politician Bjørn Arild Gram.
  • A. Grammatiko
    Grammatiko is a village in the East Attica region of Greece, known for its traditional character and proximity to the Marathon area.
  • B. Gramatiko
    Gramatiko is the grammar section of the Fundamento de Esperanto, outlining the core grammatical rules of the Esperanto language.
  • C. .kg
    .kg is the country code top-level domain (ccTLD) assigned to Kyrgyzstan for use in internet addresses.
  • D. Gros
    Gros is a French surname most famously borne by Antoine-Jean Gros, a prominent Napoleonic-era painter known for his dramatic historical and battle scenes.
  • E. Gradelle
    Gradelle is a residential neighborhood within the municipality of Chêne-Bougeries in the canton of Geneva, Switzerland.
  • F. None of above. chosen

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_69c008742a5c8190b9cb9c2787a3d8b3 completed March 22, 2026, 3:19 p.m.
NER Named-entity recognition batch_69c04fba86a48190984e95d5adf7c7f1 completed March 22, 2026, 8:23 p.m.
NED1 Entity disambiguation (via context triple) batch_69c108c2e1c88190a1629c6438f6c8bd completed March 23, 2026, 9:32 a.m.
NEDg Description generation batch_69c1096d5f2881909126730848ca0e78 completed March 23, 2026, 9:35 a.m.
NED2 Entity disambiguation (via description) batch_69c10b2699088190a468989beded758e completed March 23, 2026, 9:43 a.m.
Created at: March 22, 2026, 4:07 p.m.