Triple

T20415067
Position Surface form Disambiguated ID Type / Status
Subject Everlyn Sampi E500689 entity
Predicate familyName P18 FINISHED
Object Sampi
Sampi is a surname most notably borne by Australian actress Everlyn Sampi, known for her role in the film "Rabbit-Proof Fence."
E1430352 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: Sampi | Statement: [Everlyn Sampi, familyName, Sampi]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Sampi
Context triple: [Everlyn Sampi, familyName, Sampi]
  • A. Oschiri
    Oschiri is a small town and comune in the Gallura region of northern Sardinia, Italy, known for its rural landscape and archaeological sites.
  • B. Sanniki
    Sanniki is a village in central Poland known for its historical connections to notable Polish figures and its traditional Mazovian rural character.
  • C. Samaro
    Samaro is a town in Pakistan’s Sindh province, situated within the Umerkot District.
  • D. Sambir
    Sambir is a small historic city in western Ukraine known for its medieval roots and location within the Lviv Oblast.
  • E. Kanuma
    Kanuma is a regional harvest festival celebrated mainly in Andhra Pradesh and Telangana as part of the multi-day Makar Sankranti festivities, focusing on cattle worship and agricultural prosperity.
  • 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: Sampi
Triple: [Everlyn Sampi, familyName, Sampi]
Generated description
Sampi is a surname most notably borne by Australian actress Everlyn Sampi, known for her role in the film "Rabbit-Proof Fence."
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Sampi
Target entity description: Sampi is a surname most notably borne by Australian actress Everlyn Sampi, known for her role in the film "Rabbit-Proof Fence."
  • A. Oschiri
    Oschiri is a small town and comune in the Gallura region of northern Sardinia, Italy, known for its rural landscape and archaeological sites.
  • B. Sanniki
    Sanniki is a village in central Poland known for its historical connections to notable Polish figures and its traditional Mazovian rural character.
  • C. Samaro
    Samaro is a town in Pakistan’s Sindh province, situated within the Umerkot District.
  • D. Sambir
    Sambir is a small historic city in western Ukraine known for its medieval roots and location within the Lviv Oblast.
  • E. Kanuma
    Kanuma is a regional harvest festival celebrated mainly in Andhra Pradesh and Telangana as part of the multi-day Makar Sankranti festivities, focusing on cattle worship and agricultural prosperity.
  • 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_69e0b4a935588190b9446a99b37ced44 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e67a437eec8190a20c89a236dd5bc0 completed April 20, 2026, 7:10 p.m.
NED1 Entity disambiguation (via context triple) batch_6a087b284bb8819090f76ec27116c619 completed May 16, 2026, 2:11 p.m.
NEDg Description generation batch_6a08801702488190ba3122edb09cdaab completed May 16, 2026, 2:32 p.m.
NED2 Entity disambiguation (via description) batch_6a08811c9af081908d898134bf80452e completed May 16, 2026, 2:37 p.m.
Created at: April 16, 2026, 11:30 a.m.