Triple

T11605624
Position Surface form Disambiguated ID Type / Status
Subject Mary Pickford and Douglas Fairbanks E275250 entity
Predicate placeOfResidence P75 FINISHED
Object Pickfair
Pickfair was the famed Beverly Hills estate of silent film stars Mary Pickford and Douglas Fairbanks, renowned as a glamorous social hub of early Hollywood.
E936976 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: Pickfair | Statement: [Mary Pickford and Douglas Fairbanks, placeOfResidence, Pickfair]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Pickfair
Context triple: [Mary Pickford and Douglas Fairbanks, placeOfResidence, Pickfair]
  • A. Proudie
    Proudie is the surname of the fictional Bishop Proudie and his family in Anthony Trollope’s Barsetshire novels.
  • B. Pervyse
    Pervyse is a village in West Flanders, Belgium, known for its location on the World War I Yser Front and the heavy fighting that took place there.
  • C. Picken
    Picken is a surname and variant of the name Pickens, borne by various individuals across English-speaking countries.
  • D. Penelope Pitstop
    Penelope Pitstop is a pink-clad, Southern-belle race car driver and damsel-in-distress heroine from Hanna-Barbera’s classic cartoon series.
  • E. Pippy
    Pippy is an educational programming activity for the Sugar learning platform that lets children explore and write simple Python programs.
  • 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: Pickfair
Triple: [Mary Pickford and Douglas Fairbanks, placeOfResidence, Pickfair]
Generated description
Pickfair was the famed Beverly Hills estate of silent film stars Mary Pickford and Douglas Fairbanks, renowned as a glamorous social hub of early Hollywood.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Pickfair
Target entity description: Pickfair was the famed Beverly Hills estate of silent film stars Mary Pickford and Douglas Fairbanks, renowned as a glamorous social hub of early Hollywood.
  • A. Proudie
    Proudie is the surname of the fictional Bishop Proudie and his family in Anthony Trollope’s Barsetshire novels.
  • B. Pervyse
    Pervyse is a village in West Flanders, Belgium, known for its location on the World War I Yser Front and the heavy fighting that took place there.
  • C. Picken
    Picken is a surname and variant of the name Pickens, borne by various individuals across English-speaking countries.
  • D. Penelope Pitstop
    Penelope Pitstop is a pink-clad, Southern-belle race car driver and damsel-in-distress heroine from Hanna-Barbera’s classic cartoon series.
  • E. Pippy
    Pippy is an educational programming activity for the Sugar learning platform that lets children explore and write simple Python programs.
  • 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_69d6aaf84b548190ac072e4fb89ae18f completed April 8, 2026, 7:22 p.m.
NER Named-entity recognition batch_69d895502e0081909ee9c3d45d26cd91 completed April 10, 2026, 6:14 a.m.
NED1 Entity disambiguation (via context triple) batch_69ee871c3dbc8190922d125a04a9ee98 completed April 26, 2026, 9:43 p.m.
NEDg Description generation batch_69ee9cf1cb2481908bc473c87bc42d60 completed April 26, 2026, 11:17 p.m.
NED2 Entity disambiguation (via description) batch_69eecd31894481908dbd55f605c693f9 completed April 27, 2026, 2:42 a.m.
Created at: April 8, 2026, 9:38 p.m.