Triple

T3004997
Position Surface form Disambiguated ID Type / Status
Subject Shina E81878 entity
Predicate closelyRelatedTo P37 FINISHED
Object Brokskat
Brokskat is a Dardic language spoken in parts of northern Pakistan and India, closely related to the Shina language.
E318538 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: Brokskat | Statement: [Shina, closelyRelatedTo, Brokskat]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Brokskat
Context triple: [Shina, closelyRelatedTo, Brokskat]
  • A. Barkarby
    Barkarby is a suburban district in the Stockholm urban area of Sweden, known for its residential neighborhoods, retail outlets, and the former Barkarby Airport site.
  • B. Storvreten
    Storvreten is a residential locality within Botkyrka Municipality in the Stockholm County area of Sweden.
  • C. Schierke
    Schierke is a small village in the Harz Mountains of Germany, known as a gateway to the Brocken peak and for its historic narrow-gauge railway connections and winter sports tourism.
  • D. Rombaken
    Rombaken is a fjord in northern Norway, known as an inner branch of the Ofotfjord near the town of Narvik.
  • E. Meekknoken
    Meekknoken is the highest peak on the island of Averøya in Norway, known as its most prominent natural elevation.
  • 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: Brokskat
Triple: [Shina, closelyRelatedTo, Brokskat]
Generated description
Brokskat is a Dardic language spoken in parts of northern Pakistan and India, closely related to the Shina language.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Brokskat
Target entity description: Brokskat is a Dardic language spoken in parts of northern Pakistan and India, closely related to the Shina language.
  • A. Barkarby
    Barkarby is a suburban district in the Stockholm urban area of Sweden, known for its residential neighborhoods, retail outlets, and the former Barkarby Airport site.
  • B. Storvreten
    Storvreten is a residential locality within Botkyrka Municipality in the Stockholm County area of Sweden.
  • C. Schierke
    Schierke is a small village in the Harz Mountains of Germany, known as a gateway to the Brocken peak and for its historic narrow-gauge railway connections and winter sports tourism.
  • D. Rombaken
    Rombaken is a fjord in northern Norway, known as an inner branch of the Ofotfjord near the town of Narvik.
  • E. Meekknoken
    Meekknoken is the highest peak on the island of Averøya in Norway, known as its most prominent natural elevation.
  • 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_69ad8b1c4de88190a83b7cefaa1f2842 completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69ad9a15ad9c81908255003bdb38d603 completed March 8, 2026, 3:47 p.m.
NED1 Entity disambiguation (via context triple) batch_69b12e56bbd881909680248acca30557 completed March 11, 2026, 8:56 a.m.
NEDg Description generation batch_69b12f07ec088190a63e30f8a1f7937a completed March 11, 2026, 8:59 a.m.
NED2 Entity disambiguation (via description) batch_69b1cb6571388190970bae846bfc57a2 completed March 11, 2026, 8:07 p.m.
Created at: March 8, 2026, 2:59 p.m.