Triple

T9832279
Position Surface form Disambiguated ID Type / Status
Subject Steve Morse E239014 entity
Predicate associatedBand P6597 FINISHED
Object Angelfire
Angelfire is an acoustic rock duo featuring guitarist Steve Morse and vocalist Sarah Spencer, known for its melodic, folk-influenced sound.
E824514 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: Angelfire | Statement: [Steve Morse, associatedBand, Angelfire]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Angelfire
Context triple: [Steve Morse, associatedBand, Angelfire]
  • A. Angelfire
    Angelfire is a web hosting and website-building service best known for providing free personal homepages during the early days of the consumer internet.
  • B. Xanga
    Xanga is a now largely defunct early 2000s social networking and blogging platform that allowed users to create personal blogs, share posts, and interact through comments and subscriptions.
  • C. Ning
    Ning is an online platform that enables users and organizations to create their own custom social networks and communities.
  • D. Wapserveen
    Wapserveen is a small village in the Dutch province of Drenthe, known for its rural character and surrounding natural landscapes.
  • E. Friendster
    Friendster was one of the earliest major social networking websites, popular in the early 2000s for connecting friends online before eventually declining and shutting down.
  • 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: Angelfire
Triple: [Steve Morse, associatedBand, Angelfire]
Generated description
Angelfire is an acoustic rock duo featuring guitarist Steve Morse and vocalist Sarah Spencer, known for its melodic, folk-influenced sound.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Angelfire
Target entity description: Angelfire is an acoustic rock duo featuring guitarist Steve Morse and vocalist Sarah Spencer, known for its melodic, folk-influenced sound.
  • A. Angelfire
    Angelfire is a web hosting and website-building service best known for providing free personal homepages during the early days of the consumer internet.
  • B. Xanga
    Xanga is a now largely defunct early 2000s social networking and blogging platform that allowed users to create personal blogs, share posts, and interact through comments and subscriptions.
  • C. Ning
    Ning is an online platform that enables users and organizations to create their own custom social networks and communities.
  • D. Wapserveen
    Wapserveen is a small village in the Dutch province of Drenthe, known for its rural character and surrounding natural landscapes.
  • E. Friendster
    Friendster was one of the earliest major social networking websites, popular in the early 2000s for connecting friends online before eventually declining and shutting down.
  • 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_69ca84e314108190978324a4bdb959f8 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb335623c8190902de29795bce87d completed April 2, 2026, 12:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1d5c066a08190baabf3141c10d9f3 completed April 5, 2026, 3:23 a.m.
NEDg Description generation batch_69d1d749c0c481909b3917d4c028c2df completed April 5, 2026, 3:30 a.m.
NED2 Entity disambiguation (via description) batch_69d1d7b1e4808190b9259e3e772cd274 completed April 5, 2026, 3:32 a.m.
Created at: March 30, 2026, 8:32 p.m.