Triple

T2007513
Position Surface form Disambiguated ID Type / Status
Subject Top Hat E43618 entity
Predicate cinematographyBy P1953 FINISHED
Object David Abel
David Abel was an American cinematographer active during the early to mid-20th century, known for his work on classic Hollywood films and musicals.
E224390 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: David Abel | Statement: [Top Hat, cinematographyBy, David Abel]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: David Abel
Context triple: [Top Hat, cinematographyBy, David Abel]
  • A. Dan Osborn
    Dan Osborn is a music industry figure best known as a founder of the independent record label Drag City.
  • B. Charles Hudson
    Charles Hudson was a 19th-century British mountaineer and Anglican clergyman known for his pioneering ascents in the Alps.
  • C. Jonathan Apphus
    Jonathan Apphus was a leader of the Hasmonean dynasty who served as high priest and ruler of Judea during the 2nd century BCE, continuing the Maccabean struggle for Jewish autonomy against Seleucid rule.
  • D. Philip Sabes
    Philip Sabes is a neuroscientist and entrepreneur known for his work on brain–computer interfaces and for co-founding the neurotechnology company Neuralink.
  • E. Alex Gartner
    Alex Gartner is a film producer known for his work on major Hollywood projects, including the action thriller "Triple Frontier."
  • 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: David Abel
Triple: [Top Hat, cinematographyBy, David Abel]
Generated description
David Abel was an American cinematographer active during the early to mid-20th century, known for his work on classic Hollywood films and musicals.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: David Abel
Target entity description: David Abel was an American cinematographer active during the early to mid-20th century, known for his work on classic Hollywood films and musicals.
  • A. Dan Osborn
    Dan Osborn is a music industry figure best known as a founder of the independent record label Drag City.
  • B. Charles Hudson
    Charles Hudson was a 19th-century British mountaineer and Anglican clergyman known for his pioneering ascents in the Alps.
  • C. Jonathan Apphus
    Jonathan Apphus was a leader of the Hasmonean dynasty who served as high priest and ruler of Judea during the 2nd century BCE, continuing the Maccabean struggle for Jewish autonomy against Seleucid rule.
  • D. Philip Sabes
    Philip Sabes is a neuroscientist and entrepreneur known for his work on brain–computer interfaces and for co-founding the neurotechnology company Neuralink.
  • E. Alex Gartner
    Alex Gartner is a film producer known for his work on major Hollywood projects, including the action thriller "Triple Frontier."
  • 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_69a88716e9f08190946313fdc949e3cf completed March 4, 2026, 7:25 p.m.
NER Named-entity recognition batch_69abb8999e108190a07daa01452a5dab completed March 7, 2026, 5:33 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae0ae12d708190bcfe91e3ab53f04e completed March 8, 2026, 11:48 p.m.
NEDg Description generation batch_69ae0b63b85c819096fc8ad12ace4d22 completed March 8, 2026, 11:50 p.m.
NED2 Entity disambiguation (via description) batch_69ae0bc55fcc8190bf117ef1328b8a76 completed March 8, 2026, 11:52 p.m.
Created at: March 4, 2026, 7:37 p.m.