Triple

T14618658
Position Surface form Disambiguated ID Type / Status
Subject Gabrovo E343154 entity
Predicate twinTown P1072 FINISHED
Object Haapsalu
Haapsalu is a small seaside town in western Estonia known for its historic wooden architecture, medieval castle, and traditional seaside resort and spa culture.
E1110805 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: Haapsalu | Statement: [Gabrovo, twinTown, Haapsalu]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Haapsalu
Context triple: [Gabrovo, twinTown, Haapsalu]
  • A. Jõhvi
    Jõhvi is a town in northeastern Estonia that serves as the administrative center of Ida-Viru County.
  • B. Kohtla-Järve
    Kohtla-Järve is an industrial city in northeastern Estonia known for its oil shale industry and diverse population.
  • C. Kuressaare
    Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
  • D. Maardu
    Maardu is an industrial town in northern Estonia, located just east of the capital Tallinn in Harju County.
  • E. Pärnu
    Pärnu is a coastal city in southwestern Estonia known as a popular summer resort and spa destination on the Baltic Sea.
  • 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: Haapsalu
Triple: [Gabrovo, twinTown, Haapsalu]
Generated description
Haapsalu is a small seaside town in western Estonia known for its historic wooden architecture, medieval castle, and traditional seaside resort and spa culture.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Haapsalu
Target entity description: Haapsalu is a small seaside town in western Estonia known for its historic wooden architecture, medieval castle, and traditional seaside resort and spa culture.
  • A. Jõhvi
    Jõhvi is a town in northeastern Estonia that serves as the administrative center of Ida-Viru County.
  • B. Kohtla-Järve
    Kohtla-Järve is an industrial city in northeastern Estonia known for its oil shale industry and diverse population.
  • C. Kuressaare
    Kuressaare is the main town on Estonia’s Saaremaa island, known for its well-preserved medieval castle and seaside spa resort atmosphere.
  • D. Maardu
    Maardu is an industrial town in northern Estonia, located just east of the capital Tallinn in Harju County.
  • E. Pärnu
    Pärnu is a coastal city in southwestern Estonia known as a popular summer resort and spa destination on the Baltic Sea.
  • 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_69d822dffc3c8190aa173b90761bffda completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69deb46550e48190af45f426f02579bb completed April 14, 2026, 9:40 p.m.
NED1 Entity disambiguation (via context triple) batch_69fda924c7308190931c03fbac57b0bf completed May 8, 2026, 9:13 a.m.
NEDg Description generation batch_69fdb234bc1c8190a85c802dfcfa7909 completed May 8, 2026, 9:51 a.m.
NED2 Entity disambiguation (via description) batch_69fdb36bd50c8190a8af992fe4b12bb6 completed May 8, 2026, 9:57 a.m.
Created at: April 10, 2026, 1:25 a.m.