Triple

T15071009
Position Surface form Disambiguated ID Type / Status
Subject Wilda campus E379876 entity
Predicate district P2709 FINISHED
Object Wilda
Wilda is a district of the Polish city of Poznań, known for its mix of historic architecture, industrial heritage, and growing residential and cultural areas.
E1135647 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: Wilda | Statement: [Wilda campus, district, Wilda]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Wilda
Context triple: [Wilda campus, district, Wilda]
  • A. Wilella
    Wilella is the full given name of American novelist Willa Cather, renowned for her works depicting frontier life on the Great Plains.
  • B. Wandella
    Wandella is a rural locality within New South Wales, Australia, administered as part of the Carrathool Shire local government area.
  • C. Ruviana
    Ruviana is an alternative name for Roviana, an Oceanic language spoken in the Solomon Islands.
  • D. Rineke
    Rineke is a Dutch photographer renowned for her intimate, large-scale portraits that explore identity, vulnerability, and the passage of time.
  • E. Jandaíra
    Jandaíra is a municipality in the state of Bahia, Brazil, that forms part of the broader urban and economic area surrounding the city of Salvador.
  • 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: Wilda
Triple: [Wilda campus, district, Wilda]
Generated description
Wilda is a district of the Polish city of Poznań, known for its mix of historic architecture, industrial heritage, and growing residential and cultural areas.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Wilda
Target entity description: Wilda is a district of the Polish city of Poznań, known for its mix of historic architecture, industrial heritage, and growing residential and cultural areas.
  • A. Wilella
    Wilella is the full given name of American novelist Willa Cather, renowned for her works depicting frontier life on the Great Plains.
  • B. Wandella
    Wandella is a rural locality within New South Wales, Australia, administered as part of the Carrathool Shire local government area.
  • C. Ruviana
    Ruviana is an alternative name for Roviana, an Oceanic language spoken in the Solomon Islands.
  • D. Rineke
    Rineke is a Dutch photographer renowned for her intimate, large-scale portraits that explore identity, vulnerability, and the passage of time.
  • E. Jandaíra
    Jandaíra is a municipality in the state of Bahia, Brazil, that forms part of the broader urban and economic area surrounding the city of Salvador.
  • 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_69d85cd7683881908d405c1b5d7b4f7f completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69dff7f86df48190b3a2cf441fefb477 completed April 15, 2026, 8:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69fea5cd4b6c8190aa9ff73d5be31864 completed May 9, 2026, 3:11 a.m.
NEDg Description generation batch_69fea8e838b4819091e0a3d099c49059 completed May 9, 2026, 3:24 a.m.
NED2 Entity disambiguation (via description) batch_69fea986e0dc8190a56e71288c6a7ef4 completed May 9, 2026, 3:27 a.m.
Created at: April 10, 2026, 3:02 a.m.