Triple

T8500564
Position Surface form Disambiguated ID Type / Status
Subject Heather Angel E201204 entity
Predicate familyName P18 FINISHED
Object Angel
Angel is a surname of English origin borne by various notable individuals across fields such as acting, science, and sports.
 E740081 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: Angel | Statement: [Heather Angel, familyName, Angel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Angel
Context triple: [Heather Angel, familyName, Angel]
  • A. Angel
    "Angel" is a 1937 romantic comedy film directed by Ernst Lubitsch, known for its sophisticated wit and starring Marlene Dietrich, Herbert Marshall, and Melvyn Douglas.
  • B. Angel
    Angel is a winged mutant warrior in the X-Men universe, often depicted with metallic feathered wings and a conflicted, tormented nature.
  • C. Angel
    "Angel" is a romantic reggae fusion song by Shaggy, featuring Rayvon, best known for its smooth melody and chart-topping success in the early 2000s.
  • D. Angel
    Angel is a character in William Wordsworth's autobiographical poem "The Prelude," symbolizing spiritual guidance and inspiration in the poet's inner and artistic development.
  • E. Angel
    "Angel" is a dark, trip hop song by Massive Attack, known for its brooding atmosphere, slow-building intensity, and prominent use in film and television soundtracks.
  • 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: Angel
Triple: [Heather Angel, familyName, Angel]
Generated description
Angel is a surname of English origin borne by various notable individuals across fields such as acting, science, and sports.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Angel
Target entity description: Angel is a surname of English origin borne by various notable individuals across fields such as acting, science, and sports.
  • A. Angel
    Angel is a given name used across various cultures, often associated with spiritual or celestial connotations.
  • B. Angel
    An angel is a spiritual being found in various religious traditions, typically depicted as a messenger or servant of the divine.
  • C. Angel
    Angel is a winged mutant warrior in the X-Men universe, often depicted with metallic feathered wings and a conflicted, tormented nature.
  • D. Angel
    Angel is a character in William Wordsworth's autobiographical poem "The Prelude," symbolizing spiritual guidance and inspiration in the poet's inner and artistic development.
  • E. Angel
    Angel is a vibrant district in central London known for its bustling high street, cultural venues, and lively dining and nightlife scene.
  • 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_69ca831fe47c8190b5c57b456d2aefa0 completed March 30, 2026, 2:05 p.m.
NER Named-entity recognition batch_69cbe5996ce88190956cb3f8d9ad3daf completed March 31, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_69ce6d1c2ce4819082c92484d3865edf completed April 2, 2026, 1:20 p.m.
NEDg Description generation batch_69ce6e69213c8190add7eb9cc74b1a33 completed April 2, 2026, 1:26 p.m.
NED2 Entity disambiguation (via description) batch_69ce6f28ae6481909a8a13613f3eb5e0 completed April 2, 2026, 1:29 p.m.
Created at: March 30, 2026, 6:14 p.m.