Triple

T9548859
Position Surface form Disambiguated ID Type / Status
Subject Melanie Lynskey E230366 entity
Predicate televisionSeriesAppearance P57975 FINISHED
Object Candy
"Candy" is a true-crime drama miniseries that dramatizes the real-life case of Texas housewife Candy Montgomery, who was accused of murdering her friend Betty Gore in 1980.
 E805086 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: Candy | Statement: [Melanie Lynskey, televisionSeriesAppearance, Candy]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Candy
Context triple: [Melanie Lynskey, televisionSeriesAppearance, Candy]
  • A. Candy
    Candy is a common English surname shared by various individuals, including the late Canadian actor and comedian John Candy.
  • B. Candy
    "Candy" is a 2012 pop single by British singer Robbie Williams, known for its catchy, upbeat melody and chart-topping success in several countries.
  • C. Candy
    "Candy" is a song by the band Broken Silence.
  • D. Candy
    "Candy" is a 1968 satirical comedy film, loosely based on Voltaire’s "Candide," known for its psychedelic style and ensemble cast including Anita Pallenberg, Marlon Brando, and Ringo Starr.
  • E. Candy
    Candy is a fictional character who appears in the setting known as Candy's Room.
  • 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: Candy
Triple: [Melanie Lynskey, televisionSeriesAppearance, Candy]
Generated description
"Candy" is a true-crime drama miniseries that dramatizes the real-life case of Texas housewife Candy Montgomery, who was accused of murdering her friend Betty Gore in 1980.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Candy
Target entity description: "Candy" is a true-crime drama miniseries that dramatizes the real-life case of Texas housewife Candy Montgomery, who was accused of murdering her friend Betty Gore in 1980.
  • A. Candy chosen
    "Candy" is a true-crime drama miniseries centered on Texas housewife Candy Montgomery, who was accused of a brutal axe murder in 1980.
  • B. Candy
    "Candy" is a 1968 satirical comedy film, loosely based on Voltaire’s "Candide," known for its psychedelic style and ensemble cast including Anita Pallenberg, Marlon Brando, and Ringo Starr.
  • C. Candy
    Candy is a fictional character who appears in the setting known as Candy's Room.
  • D. Candy
    "Candy" is a 2012 pop single by British singer Robbie Williams, known for its catchy, upbeat melody and chart-topping success in several countries.
  • E. Candy
    "Candy" is a song by the band Broken Silence.
  • F. None of above.

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_69ca847c70b8819088a0a0bad64a50d6 completed March 30, 2026, 2:11 p.m.
NER Named-entity recognition batch_69cd99059138819088ae54b26df979cf completed April 1, 2026, 10:15 p.m.
NED1 Entity disambiguation (via context triple) batch_69d1528068a481908d5c8037b4591db5 completed April 4, 2026, 6:03 p.m.
NEDg Description generation batch_69d153c26b8481908298b32918666562 completed April 4, 2026, 6:09 p.m.
NED2 Entity disambiguation (via description) batch_69d15445e7a88190accd19c53a6170bb completed April 4, 2026, 6:11 p.m.
Created at: March 30, 2026, 8:02 p.m.