Triple

T10794825
Position Surface form Disambiguated ID Type / Status
Subject Zanjan Province E254676 entity
Predicate hasCity P316 FINISHED
Object Tarom
Tarom is a city in Iran known for its location within Zanjan Province and its surrounding mountainous, agricultural landscape.
E910968 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: Tarom | Statement: [Zanjan Province, hasCity, Tarom]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tarom
Context triple: [Zanjan Province, hasCity, Tarom]
  • A. Tarom
    Tarom is Romania's national flag carrier airline, operating domestic and international flights primarily from its hub in Bucharest.
  • B. Tighina
    Tighina is a historic city in present-day Moldova, also known as Bender, which has long held strategic importance on the Dniester River.
  • C. Târgoviște
    Târgoviște is a historic city in southern Romania, known as a former Wallachian capital and the site where Nicolae Ceaușescu was executed in 1989.
  • D. Arad
    Arad is a small Israeli city on the edge of the Negev Desert, known for its dry climate, desert landscapes, and proximity to the Dead Sea and Masada.
  • E. Arad
    Arad is a major city in western Romania known for its historical architecture, cultural heritage, and role as an important industrial and transportation hub near the Hungarian border.
  • 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: Tarom
Triple: [Zanjan Province, hasCity, Tarom]
Generated description
Tarom is a city in Iran known for its location within Zanjan Province and its surrounding mountainous, agricultural landscape.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tarom
Target entity description: Tarom is a city in Iran known for its location within Zanjan Province and its surrounding mountainous, agricultural landscape.
  • A. Tarom
    Tarom is Romania's national flag carrier airline, operating domestic and international flights primarily from its hub in Bucharest.
  • B. Tighina
    Tighina is a historic city in present-day Moldova, also known as Bender, which has long held strategic importance on the Dniester River.
  • C. Târgoviște
    Târgoviște is a historic city in southern Romania, known as a former Wallachian capital and the site where Nicolae Ceaușescu was executed in 1989.
  • D. Arad
    Arad is a small Israeli city on the edge of the Negev Desert, known for its dry climate, desert landscapes, and proximity to the Dead Sea and Masada.
  • E. Arad
    Arad is a major city in western Romania known for its historical architecture, cultural heritage, and role as an important industrial and transportation hub near the Hungarian border.
  • 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_69d6aa61c15c8190a1839550c56e75e1 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d733321dd881909dcd4224dfa9822a completed April 9, 2026, 5:03 a.m.
NED1 Entity disambiguation (via context triple) batch_69e49658b5a48190813dcf114d92be8e completed April 19, 2026, 8:46 a.m.
NEDg Description generation batch_69e49a97db808190aa22d6a103a13e58 completed April 19, 2026, 9:04 a.m.
NED2 Entity disambiguation (via description) batch_69e49d71e81c8190af73931ed30e04be completed April 19, 2026, 9:16 a.m.
Created at: April 8, 2026, 9:17 p.m.