Triple

T379824
Position Surface form Disambiguated ID Type / Status
Subject The Wizard of Oz E8653 entity
Predicate character P662 FINISHED
Object Glinda the Good Witch
Glinda the Good Witch is a benevolent and powerful sorceress from L. Frank Baum’s Oz universe, best known for guiding Dorothy on her journey home.
E48453 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: Glinda the Good Witch | Statement: [The Wizard of Oz, character, Glinda the Good Witch]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Glinda the Good Witch
Context triple: [The Wizard of Oz, character, Glinda the Good Witch]
  • A. Princess Ozma
    Princess Ozma is a fictional royal character from L. Frank Baum’s Oz book series, serving as the rightful ruler of the Land of Oz.
  • B. Barbara
    Barbara is a feminine given name of Greek origin that has been widely used in many cultures and languages.
  • C. Mary Jane Gumm
    Mary Jane Gumm was an American vaudeville and film performer, best known as one of Judy Garland’s older sisters and early singing partners in the Gumm Sisters act.
  • D. Doris
    Doris is an Oceanid from Greek mythology, known as the wife of the sea god Nereus and mother of the Nereids.
  • E. Hilda
    Hilda is the middle name of Margaret Thatcher, the former Prime Minister of the United Kingdom.
  • 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: Glinda the Good Witch
Triple: [The Wizard of Oz, character, Glinda the Good Witch]
Generated description
Glinda the Good Witch is a benevolent and powerful sorceress from L. Frank Baum’s Oz universe, best known for guiding Dorothy on her journey home.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Glinda the Good Witch
Target entity description: Glinda the Good Witch is a benevolent and powerful sorceress from L. Frank Baum’s Oz universe, best known for guiding Dorothy on her journey home.
  • A. Princess Ozma
    Princess Ozma is a fictional royal character from L. Frank Baum’s Oz book series, serving as the rightful ruler of the Land of Oz.
  • B. Barbara
    Barbara is a feminine given name of Greek origin that has been widely used in many cultures and languages.
  • C. Mary Jane Gumm
    Mary Jane Gumm was an American vaudeville and film performer, best known as one of Judy Garland’s older sisters and early singing partners in the Gumm Sisters act.
  • D. Doris
    Doris is an Oceanid from Greek mythology, known as the wife of the sea god Nereus and mother of the Nereids.
  • E. Hilda
    Hilda is the middle name of Margaret Thatcher, the former Prime Minister of the United Kingdom.
  • 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_69a2e7f47dd08190a4e294ccbbe46cd4 completed Feb. 28, 2026, 1:04 p.m.
NER Named-entity recognition batch_69a2ec2b07248190979229bad3a741c9 completed Feb. 28, 2026, 1:22 p.m.
NED1 Entity disambiguation (via context triple) batch_69a3faffa5848190b77503516f3d0ba6 completed March 1, 2026, 8:38 a.m.
NEDg Description generation batch_69a3fb912d9881909d8eb02cdae70163 completed March 1, 2026, 8:40 a.m.
NED2 Entity disambiguation (via description) batch_69a3fd99e73c8190b5a92856ca0a4b82 completed March 1, 2026, 8:49 a.m.
Created at: Feb. 28, 2026, 1:08 p.m.