Triple

T15796046
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth South E382980 entity
Predicate stateElectorate P11212 FINISHED
Object Elizabeth
Elizabeth is an electoral district in South Australia represented in the state's House of Assembly.
E389234 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: Elizabeth | Statement: [Elizabeth South, stateElectorate, Elizabeth]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Context triple: [Elizabeth South, stateElectorate, Elizabeth]
  • A. Elizabeth
    Elizabeth is a key character in Nathaniel Hawthorne’s short story “The Minister’s Black Veil,” serving as Reverend Hooper’s fiancée whose reaction to his mysterious veil highlights themes of isolation and the fear of hidden sin.
  • B. Elizabeth
    Elizabeth is the full given name of Betsy McCaughey, an American politician, writer, and former lieutenant governor of New York.
  • C. Elizabeth
    Elizabeth is the given name of Princess Elizabeth of Yugoslavia, a Yugoslav royal and public figure.
  • D. Elizabeth
    Elizabeth was a German noblewoman who held the title of Landgravine of Hesse-Homburg.
  • E. Elizabeth
    Elizabeth is the given first name of American actress Bess Armstrong, known for her work in film and television since the late 1970s.
  • 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: Elizabeth
Triple: [Elizabeth South, stateElectorate, Elizabeth]
Generated description
Elizabeth is an electoral district in South Australia represented in the state's House of Assembly.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Elizabeth
Target entity description: Elizabeth is an electoral district in South Australia represented in the state's House of Assembly.
  • A. Elizabeth chosen
    Elizabeth is a suburban electorate in South Australia known for its working-class community and industrial heritage within the northern Adelaide region.
  • B. Elizabeth
    Elizabeth is a city in northeastern New Jersey that forms part of the greater New York metropolitan area.
  • C. Elizabeth
    Elizabeth is the full given name of American politician Lizzie Fletcher, a U.S. Representative from Texas.
  • D. Elizabeth
    Elizabeth is a small town in Colorado known for its rural character and proximity to the Denver metropolitan area.
  • E. Elizabeth
    Elizabeth is the full given name of American attorney and politician Liz Cheney, a prominent conservative figure and former U.S. Representative from Wyoming.
  • 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_69d86da16e188190b89af699f1ed0bfe completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e0b4dc887081909d682ae153f06d97 completed April 16, 2026, 10:07 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff998981088190b9ce9d99c0481e21 completed May 9, 2026, 8:31 p.m.
NEDg Description generation batch_69ff9a215e7c8190a2b40fb027a38317 completed May 9, 2026, 8:33 p.m.
NED2 Entity disambiguation (via description) batch_69ff9a77d6d88190817158c30c56d70c completed May 9, 2026, 8:35 p.m.
Created at: April 10, 2026, 4:48 a.m.