Triple

T9207822
Position Surface form Disambiguated ID Type / Status
Subject Bojnord E221030 entity
Predicate hasAttraction P105 FINISHED
Object Besh Qardash spring
Besh Qardash spring is a historic natural spring and popular recreational site near Bojnord in North Khorasan Province, Iran, known for its scenic setting and cultural significance.
E785970 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: Besh Qardash spring | Statement: [Bojnord, hasAttraction, Besh Qardash spring]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Besh Qardash spring
Context triple: [Bojnord, hasAttraction, Besh Qardash spring]
  • A. Arugot Spring
    Arugot Spring is a popular desert oasis and hiking destination in the Ein Gedi Nature Reserve near the Dead Sea in Israel, known for its waterfalls, pools, and lush vegetation.
  • B. Lympia spring
    Lympia spring is a historic freshwater source in Nice, France, traditionally associated with the area around the city’s port.
  • C. Bakhah
    Bakhah is a village in Syria known as one of the few remaining communities where Western Neo-Aramaic is still actively spoken.
  • D. Mrgashat
    Mrgashat is a village in Armenia located within the country's western Armavir Province.
  • E. Sadeh
    Sadeh is an ancient Persian mid-winter fire festival that celebrates the triumph of light and warmth over darkness and cold.
  • 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: Besh Qardash spring
Triple: [Bojnord, hasAttraction, Besh Qardash spring]
Generated description
Besh Qardash spring is a historic natural spring and popular recreational site near Bojnord in North Khorasan Province, Iran, known for its scenic setting and cultural significance.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Besh Qardash spring
Target entity description: Besh Qardash spring is a historic natural spring and popular recreational site near Bojnord in North Khorasan Province, Iran, known for its scenic setting and cultural significance.
  • A. Arugot Spring
    Arugot Spring is a popular desert oasis and hiking destination in the Ein Gedi Nature Reserve near the Dead Sea in Israel, known for its waterfalls, pools, and lush vegetation.
  • B. Lympia spring
    Lympia spring is a historic freshwater source in Nice, France, traditionally associated with the area around the city’s port.
  • C. Bakhah
    Bakhah is a village in Syria known as one of the few remaining communities where Western Neo-Aramaic is still actively spoken.
  • D. Mrgashat
    Mrgashat is a village in Armenia located within the country's western Armavir Province.
  • E. Sadeh
    Sadeh is an ancient Persian mid-winter fire festival that celebrates the triumph of light and warmth over darkness and cold.
  • 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_69ca83e9d0e081908bdb71097201a06c completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd9b217008190a0ab4971dd4a8899 completed April 1, 2026, 8:39 a.m.
NED1 Entity disambiguation (via context triple) batch_69d065e49fcc81909ddb838a8ad28c57 completed April 4, 2026, 1:14 a.m.
NEDg Description generation batch_69d0676ea53c81908b16dfce6810f6b0 completed April 4, 2026, 1:20 a.m.
NED2 Entity disambiguation (via description) batch_69d0684c1a108190bc7fdfdced16e24c completed April 4, 2026, 1:24 a.m.
Created at: March 30, 2026, 7:26 p.m.