Triple

T15636844
Position Surface form Disambiguated ID Type / Status
Subject Gdańsk Old Town E375966 entity
Predicate hasLandmark P105 FINISHED
Object Main Town Hall
Main Town Hall is a historic Gothic-Renaissance municipal building and prominent architectural landmark located in the heart of Gdańsk’s Old Town.
E1168373 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: Main Town Hall | Statement: [Gdańsk Old Town, hasLandmark, Main Town Hall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Main Town Hall
Context triple: [Gdańsk Old Town, hasLandmark, Main Town Hall]
  • A. Town Hall
    Town Hall is a historic civic building in Berwick-upon-Tweed that has long served as a center for local government and community events.
  • B. Town Hall
    Town Hall is a prominent civic building in Clonmel, Ireland, serving as a central venue for local government and community events.
  • C. Town Hall
    Town Hall is a prominent civic and cultural building in Middlesbrough, England, known for hosting concerts, performances, and community events.
  • D. Town Hall
    Town Hall is a prominent civic building in Leamington Spa that serves as a focal point for local government and community events.
  • E. Town Hall
    Town Hall is a major civic building and historic landmark in central Sydney, commonly used for government functions, public events, and cultural activities.
  • 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: Main Town Hall
Triple: [Gdańsk Old Town, hasLandmark, Main Town Hall]
Generated description
Main Town Hall is a historic Gothic-Renaissance municipal building and prominent architectural landmark located in the heart of Gdańsk’s Old Town.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Main Town Hall
Target entity description: Main Town Hall is a historic Gothic-Renaissance municipal building and prominent architectural landmark located in the heart of Gdańsk’s Old Town.
  • A. Town Hall
    Town Hall is a historic civic building in Berwick-upon-Tweed that has long served as a center for local government and community events.
  • B. Town Hall
    Town Hall is a prominent civic building in Clonmel, Ireland, serving as a central venue for local government and community events.
  • C. Town Hall
    Town Hall is a major civic building and historic landmark in central Sydney, commonly used for government functions, public events, and cultural activities.
  • D. Town Hall
    Town Hall is a prominent civic and cultural building in Middlesbrough, England, known for hosting concerts, performances, and community events.
  • E. Town Hall
    Town Hall is a prominent civic building in Leamington Spa that serves as a focal point for local government and community events.
  • 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_69d85cd035a48190b73d5579ab73969a completed April 10, 2026, 2:13 a.m.
NER Named-entity recognition batch_69e04eba51f08190ac5d9de7fc89405a completed April 16, 2026, 2:51 a.m.
NED1 Entity disambiguation (via context triple) batch_69ff5f4923ac8190a03fe1f2c878c27e completed May 9, 2026, 4:22 p.m.
NEDg Description generation batch_69ff608017d481909dab53450fbdb1e4 completed May 9, 2026, 4:27 p.m.
NED2 Entity disambiguation (via description) batch_69ff61929780819096537342305ea505 completed May 9, 2026, 4:32 p.m.
Created at: April 10, 2026, 4:14 a.m.