Triple

T23052911
Position Surface form Disambiguated ID Type / Status
Subject Shane West E574069 entity
Predicate notableWork P4 FINISHED
Object Salem
Salem is a supernatural horror television series that reimagines the infamous Salem witch trials with a dark, fictionalized narrative.
E444348 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: [Shane West, notableWork, Salem]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Salem
Context triple: [Shane West, notableWork, 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 municipality in the Bodenseekreis district of the German state of Baden-Württemberg, known for its historic Salem Abbey and proximity to Lake Constance.
  • 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: [Shane West, notableWork, Salem]
Generated description
Salem is a supernatural horror television series that reimagines the infamous Salem witch trials with a dark, fictionalized narrative.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Salem
Target entity description: Salem is a supernatural horror television series that reimagines the infamous Salem witch trials with a dark, fictionalized narrative.
  • A. Salem chosen
    Salem is a supernatural horror television series that reimagines the infamous Salem witch trials with a dark, fictionalized narrative.
  • B. Salem
    Salem is the fictional Midwestern town that serves as the primary setting for the long-running American soap opera "Days of Our Lives."
  • C. Salem
    Salem is a historic coastal city in Massachusetts best known for the 1692 witch trials and its well-preserved colonial architecture.
  • D. 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.
  • 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.

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_69e245ba7ae48190be606dbc54120e39 completed April 17, 2026, 2:37 p.m.
NER Named-entity recognition batch_69f1867dfac48190bf300f85d2907854 completed April 29, 2026, 4:18 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0c0ae036908190a6cdcb74e0d28f82 completed May 19, 2026, 7:01 a.m.
NEDg Description generation batch_6a0c0e2dd7908190afa879304ef3ed17 completed May 19, 2026, 7:15 a.m.
NED2 Entity disambiguation (via description) batch_6a0c0eaa7f8c81908110341d34d92537 completed May 19, 2026, 7:18 a.m.
Created at: April 17, 2026, 3:54 p.m.