Triple

T3704310
Position Surface form Disambiguated ID Type / Status
Subject Elizabeth, South Australia E80853 entity
Predicate federalElectorate P1971 FINISHED
Object Spence
Spence is an Australian federal electoral division in South Australia, represented in the House of Representatives.
 E382973 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: Spence | Statement: [Elizabeth, South Australia, federalElectorate, Spence]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Spence
Context triple: [Elizabeth, South Australia, federalElectorate, Spence]
  • A. Spencer
    Spencer is the middle name of American author and aviator Anne Spencer Lindbergh, reflecting her family’s naming tradition.
  • B. Spencer
    Spencer is a masculine given name of English origin, historically associated with roles such as steward or dispenser and borne by various notable figures.
  • C. Spencer
    Spencer is a 2021 biographical psychological drama film depicting Princess Diana during a tense Christmas holiday with the British royal family, starring Kristen Stewart in the lead role.
  • D. Spencer
    Spencer is a small town in central Massachusetts known for its New England character and historic mill village roots.
  • E. Spencer Brook
    Spencer Brook is a smaller tributary stream that feeds into New York’s Croton River within the Croton River watershed system.
  • 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: Spence
Triple: [Elizabeth, South Australia, federalElectorate, Spence]
Generated description
Spence is an Australian federal electoral division in South Australia, represented in the House of Representatives.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Spence
Target entity description: Spence is an Australian federal electoral division in South Australia, represented in the House of Representatives.
  • A. Spencer
    Spencer is a 2021 biographical psychological drama film depicting Princess Diana during a tense Christmas holiday with the British royal family, starring Kristen Stewart in the lead role.
  • B. Spencer
    Spencer is a masculine given name of English origin, historically associated with roles such as steward or dispenser and borne by various notable figures.
  • C. Spencer
    Spencer is the middle name of American author and aviator Anne Spencer Lindbergh, reflecting her family’s naming tradition.
  • D. Spencer
    Spencer is a small town in central Massachusetts known for its New England character and historic mill village roots.
  • E. Spencer Brook
    Spencer Brook is a smaller tributary stream that feeds into New York’s Croton River within the Croton River watershed system.
  • 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_69ad8b1793888190a5f70e4b21dc05a1 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adc54aaac88190b775dba2513b6d4a completed March 8, 2026, 6:51 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4cdfada708190ba6ae04bad52bb2b completed March 14, 2026, 2:54 a.m.
NEDg Description generation batch_69b4d2be3be4819082c9627099b78e32 completed March 14, 2026, 3:15 a.m.
NED2 Entity disambiguation (via description) batch_69b4d395336881908a942dd408560a81 completed March 14, 2026, 3:18 a.m.
Created at: March 8, 2026, 3:33 p.m.