Triple

T20206360
Position Surface form Disambiguated ID Type / Status
Subject Bodenseekreis E493361 entity
Predicate hasMunicipality P847 FINISHED
Object Salem
Salem is a municipality in the Bodenseekreis district of the German state of Baden-Württemberg, known for its historic Salem Abbey and proximity to Lake Constance.
E1420032 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: Salem | Statement: [Bodenseekreis, hasMunicipality, Salem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salem
Context triple: [Bodenseekreis, hasMunicipality, Salem]
  • A. Salem
    Salem is a mid-sized city in the Willamette Valley of the U.S. Pacific Northwest known for its government institutions and agricultural surroundings.
  • B. Salem
    Salem is a major city in the Indian state of Tamil Nadu, historically significant as an important administrative and commercial center under British rule.
  • C. Salem
    Salem was the original name of the small town now known as Marshall in Fauquier County, Virginia.
  • D. Salem
    Salem is a small city in Utah County, Utah, known for its scenic pond, suburban character, and location within the Provo–Orem metropolitan area.
  • E. Salem
    Salem is a character voiced by Jen Taylor, best known as the primary antagonist in the animated web series RWBY.
  • 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: Salem
Triple: [Bodenseekreis, hasMunicipality, Salem]
Generated description
Salem is a municipality in the Bodenseekreis district of the German state of Baden-Württemberg, known for its historic Salem Abbey and proximity to Lake Constance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Salem
Target entity description: Salem is a municipality in the Bodenseekreis district of the German state of Baden-Württemberg, known for its historic Salem Abbey and proximity to Lake Constance.
  • A. Salem
    Salem is a locality and municipality in Stockholm County, Sweden, known as a suburban residential area within the Greater Stockholm region.
  • B. Salem
    Salem is a small city in Utah County, Utah, known for its scenic pond, suburban character, and location within the Provo–Orem metropolitan area.
  • C. Salem
    Salem is a mid-sized city in the Willamette Valley of the U.S. Pacific Northwest known for its government institutions and agricultural surroundings.
  • D. Salem
    Salem is a major city in the Indian state of Tamil Nadu, historically significant as an important administrative and commercial center under British rule.
  • E. Salem
    Salem is a historic town in southwestern New Jersey known as one of the earliest English settlements in the region and a former colonial county seat.
  • 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_69da6269614c8190bb40475d9d477358 completed April 11, 2026, 3:02 p.m.
NER Named-entity recognition batch_69e66d922ebc8190ae012da8ceba74dd completed April 20, 2026, 6:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a08551a0dd8819092042277a39e643a completed May 16, 2026, 11:29 a.m.
NEDg Description generation batch_6a0855ea027481908eebd5cff8ac97fb completed May 16, 2026, 11:32 a.m.
NED2 Entity disambiguation (via description) batch_6a08568fa1748190b4e2c21fc3ec0b63 completed May 16, 2026, 11:35 a.m.
Created at: April 11, 2026, 11:38 p.m.