Triple

T9813507
Position Surface form Disambiguated ID Type / Status
Subject Zanjan E238337 entity
Predicate locatedOnRiver P165 FINISHED
Object Zanjanrud
Zanjanrud is a river in northwestern Iran that flows through the city of Zanjan and its surrounding region.
 E823275 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: Zanjanrud | Statement: [Zanjan, locatedOnRiver, Zanjanrud]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zanjanrud
Context triple: [Zanjan, locatedOnRiver, Zanjanrud]
  • A. Bijar
    Bijar is a town in Iran renowned for producing exceptionally durable, densely knotted Persian carpets known for their rich colors and intricate designs.
  • B. Sorkheh
    Sorkheh is a small city in north-central Iran known for its location within Semnan Province and its semi-arid climate.
  • C. Shirakavan
    Shirakavan was a medieval Armenian city that served as one of the principal royal centers of the Bagratid Kingdom of Armenia.
  • D. Zafaraniyeh
    Zafaraniyeh is an affluent residential neighborhood in northern Tehran, Iran, known for its upscale homes and proximity to the Alborz mountains.
  • E. Margilan
    Margilan is a historic city in eastern Uzbekistan renowned as a traditional center of silk production and trade along the Silk Road.
  • 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: Zanjanrud
Triple: [Zanjan, locatedOnRiver, Zanjanrud]
Generated description
Zanjanrud is a river in northwestern Iran that flows through the city of Zanjan and its surrounding region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zanjanrud
Target entity description: Zanjanrud is a river in northwestern Iran that flows through the city of Zanjan and its surrounding region.
  • A. Bijar
    Bijar is a town in Iran renowned for producing exceptionally durable, densely knotted Persian carpets known for their rich colors and intricate designs.
  • B. Sorkheh
    Sorkheh is a small city in north-central Iran known for its location within Semnan Province and its semi-arid climate.
  • C. Shirakavan
    Shirakavan was a medieval Armenian city that served as one of the principal royal centers of the Bagratid Kingdom of Armenia.
  • D. Zafaraniyeh
    Zafaraniyeh is an affluent residential neighborhood in northern Tehran, Iran, known for its upscale homes and proximity to the Alborz mountains.
  • E. Margilan
    Margilan is a historic city in eastern Uzbekistan renowned as a traditional center of silk production and trade along the Silk Road.
  • 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_69ca84defac48190abc1148804f184c1 completed March 30, 2026, 2:12 p.m.
NER Named-entity recognition batch_69cdb22410208190b82b81a4df800f80 completed April 2, 2026, 12:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69d1cc63c450819091e57030a48e7d88 completed April 5, 2026, 2:43 a.m.
NEDg Description generation batch_69d1cce3d9d481909eaf7278dfe20955 completed April 5, 2026, 2:45 a.m.
NED2 Entity disambiguation (via description) batch_69d1cd5d1670819085c58ff8889318af completed April 5, 2026, 2:47 a.m.
Created at: March 30, 2026, 8:30 p.m.