Triple

T10004451
Position Surface form Disambiguated ID Type / Status
Subject Elsa Hosk E198207 entity
Predicate familyName P18 FINISHED
Object Hosk
Hosk is a Swedish surname most notably borne by supermodel and former Victoria’s Secret Angel Elsa Hosk.
 E835856 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: Hosk | Statement: [Elsa Hosk, familyName, Hosk]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Hosk
Context triple: [Elsa Hosk, familyName, Hosk]
  • A. Marlohe
    Marlohe is the surname of French actress and model Bérénice Marlohe, best known for her role as Sévérine in the James Bond film "Skyfall."
  • B. Unhos
    Unhos is a civil parish in the municipality of Loures, within the Lisbon District of Portugal.
  • C. Hosle
    Hosle is a residential area and neighborhood located within the municipality of Bærum in Norway.
  • D. Angourie
    Angourie is a small coastal village in New South Wales, Australia, renowned for its surf breaks and scenic beaches.
  • E. Koho
    Koho is an Austroasiatic language spoken by the Koho ethnic group in Vietnam’s Central Highlands.
  • 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: Hosk
Triple: [Elsa Hosk, familyName, Hosk]
Generated description
Hosk is a Swedish surname most notably borne by supermodel and former Victoria’s Secret Angel Elsa Hosk.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Hosk
Target entity description: Hosk is a Swedish surname most notably borne by supermodel and former Victoria’s Secret Angel Elsa Hosk.
  • A. Marlohe
    Marlohe is the surname of French actress and model Bérénice Marlohe, best known for her role as Sévérine in the James Bond film "Skyfall."
  • B. Unhos
    Unhos is a civil parish in the municipality of Loures, within the Lisbon District of Portugal.
  • C. Hosle
    Hosle is a residential area and neighborhood located within the municipality of Bærum in Norway.
  • D. Angourie
    Angourie is a small coastal village in New South Wales, Australia, renowned for its surf breaks and scenic beaches.
  • E. Koho
    Koho is an Austroasiatic language spoken by the Koho ethnic group in Vietnam’s Central Highlands.
  • 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_69ca830fcca48190bbbd9b20c233835f completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cdcd141ec08190b857fe7e15a8df93 completed April 2, 2026, 1:57 a.m.
NED1 Entity disambiguation (via context triple) batch_69d26a5058a08190b850d30ca0ee8bc8 completed April 5, 2026, 1:57 p.m.
NEDg Description generation batch_69d26b6d52e8819082fed0bfdaf48e4c completed April 5, 2026, 2:02 p.m.
NED2 Entity disambiguation (via description) batch_69d26c3d5f2081909bf1a1565b66eca9 completed April 5, 2026, 2:05 p.m.
Created at: March 30, 2026, 8:51 p.m.