Triple

T23446194
Position Surface form Disambiguated ID Type / Status
Subject Susan Bones E565543 entity
Predicate familyName P18 FINISHED
Object Bones
Bones is a British wizarding family name in the Harry Potter series, notably borne by characters such as Susan Bones and her relatives in the Ministry of Magic.
E1585510 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: Bones | Statement: [Susan Bones, familyName, Bones]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Bones
Context triple: [Susan Bones, familyName, Bones]
  • A. Bones
    "Bones" is the official theme song used for WWE's WrestleMania 29 event.
  • B. Bones
    "Bones" is a 2022 pop-rock single by Imagine Dragons known for its dark, upbeat sound and themes of mortality and resilience.
  • C. Bones
    "Bones" is a moody, guitar-driven alternative rock song by Radiohead from their 1995 album *The Bends*, noted for its themes of physical and emotional fragility.
  • D. Bones
    Bones is the widely recognized nickname of Jon Jones, the dominant American mixed martial artist and multiple-time UFC light heavyweight champion.
  • E. Bones
    Bones is a critically acclaimed novel by Zimbabwean writer Chenjerai Hove that explores the human cost of colonialism and war through the life of a rural woman.
  • 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: Bones
Triple: [Susan Bones, familyName, Bones]
Generated description
Bones is a British wizarding family name in the Harry Potter series, notably borne by characters such as Susan Bones and her relatives in the Ministry of Magic.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Bones
Target entity description: Bones is a British wizarding family name in the Harry Potter series, notably borne by characters such as Susan Bones and her relatives in the Ministry of Magic.
  • A. Bones
    Bones is the nickname of Bones McKinney, a notable American basketball player and coach from the mid-20th century.
  • B. Bones
    Bones is the widely recognized nickname of Jon Jones, the dominant American mixed martial artist and multiple-time UFC light heavyweight champion.
  • C. Bones
    Bones is a critically acclaimed novel by Zimbabwean writer Chenjerai Hove that explores the human cost of colonialism and war through the life of a rural woman.
  • D. Bones
    Bones is the nickname of Dr. Leonard McCoy, the irascible yet compassionate chief medical officer aboard the starship Enterprise in the Star Trek franchise.
  • E. Bones
    Bones is a renowned Japanese animation studio known for producing high-quality, visually dynamic anime series such as Fullmetal Alchemist, My Hero Academia, and Mob Psycho 100.
  • 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_69e24584f9488190bb32730bd2ce023e completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f1a64939e4819085862e7482e14879 completed April 29, 2026, 6:33 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c67b9733c8190a5bb408df3d0940a completed May 19, 2026, 1:38 p.m.
NEDg Description generation batch_6a0c7217edc881909f582f0c726d7e61 completed May 19, 2026, 2:22 p.m.
NED2 Entity disambiguation (via description) batch_6a0c76c54ba08190be8f46bacb22b6a3 completed May 19, 2026, 2:42 p.m.
Created at: April 17, 2026, 5:51 p.m.