Triple

T15372829
Position Surface form Disambiguated ID Type / Status
Subject Võru County E367591 entity
Predicate containsSettlement P847 FINISHED
Object Haanja
Haanja is a small village in southeastern Estonia known for its hilly landscape and proximity to the country’s highest point, Suur Munamägi.
E1152505 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: Haanja | Statement: [Võru County, containsSettlement, Haanja]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haanja
Context triple: [Võru County, containsSettlement, Haanja]
  • A. Mahwa
    Mahwa is a town located in the Dausa district of the Indian state of Rajasthan.
  • B. Haeju
    Haeju is a coastal city in southwestern North Korea, historically significant as a regional center and port on the Yellow Sea.
  • C. Haimoo
    Haimoo is a small village located within the municipality of Vihti in southern Finland.
  • D. Jalu
    Jalu is an oasis town in northeastern Libya known for its date palms, desert landscape, and role as a local administrative and trading center.
  • E. Hangang
    Hangang is the Korean name for the Han River, a major waterway flowing through Seoul and central to the city's landscape, history, and recreation.
  • 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: Haanja
Triple: [Võru County, containsSettlement, Haanja]
Generated description
Haanja is a small village in southeastern Estonia known for its hilly landscape and proximity to the country’s highest point, Suur Munamägi.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haanja
Target entity description: Haanja is a small village in southeastern Estonia known for its hilly landscape and proximity to the country’s highest point, Suur Munamägi.
  • A. Mahwa
    Mahwa is a town located in the Dausa district of the Indian state of Rajasthan.
  • B. Haeju
    Haeju is a coastal city in southwestern North Korea, historically significant as a regional center and port on the Yellow Sea.
  • C. Haimoo
    Haimoo is a small village located within the municipality of Vihti in southern Finland.
  • D. Jalu
    Jalu is an oasis town in northeastern Libya known for its date palms, desert landscape, and role as a local administrative and trading center.
  • E. Hangang
    Hangang is the Korean name for the Han River, a major waterway flowing through Seoul and central to the city's landscape, history, and recreation.
  • 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_69d85a1483788190ad93c2748e8af34b completed April 10, 2026, 2:01 a.m.
NER Named-entity recognition batch_69e03e5c1d548190930bfaf0861595ae completed April 16, 2026, 1:41 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff0b528f408190b66d3d6e10e90a43 completed May 9, 2026, 10:24 a.m.
NEDg Description generation batch_69ff0bc7dfe48190a05c2b826c7fd35c completed May 9, 2026, 10:26 a.m.
NED2 Entity disambiguation (via description) batch_69ff0c51c6c081908943ddb409655ed6 completed May 9, 2026, 10:28 a.m.
Created at: April 10, 2026, 3:18 a.m.