Triple

T16866956
Position Surface form Disambiguated ID Type / Status
Subject Vecrīga E410066 entity
Predicate hasPart P35 FINISHED
Object Swedish Gate
Swedish Gate is a historic city gate in Riga’s Old Town, notable as one of the few remaining medieval entrances to the former fortified city.
 E1237853 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: Swedish Gate | Statement: [Vecrīga, hasPart, Swedish Gate]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Swedish Gate
Context triple: [Vecrīga, hasPart, Swedish Gate]
  • A. Norway Gate
    Norway Gate is a historic entrance structure associated with the Kastellet fortress complex.
  • B. Musegg Gate
    Musegg Gate is one of the historic towers and entrances incorporated into Lucerne’s medieval Musegg Wall fortifications in Switzerland.
  • C. Narva Gate
    Narva Gate is a historic triumphal arch in Saint Petersburg, Russia, commemorating Russian military victories and serving as a notable architectural landmark.
  • D. Londorossi Gate
    Londorossi Gate is a primary western entrance and registration point to Mount Kilimanjaro National Park, commonly used by climbers beginning the Lemosho Route.
  • E. Erer Gate
    Erer Gate is one of the historic gateways in the ancient walled city of Harar Jugol in eastern Ethiopia.
  • 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: Swedish Gate
Triple: [Vecrīga, hasPart, Swedish Gate]
Generated description
Swedish Gate is a historic city gate in Riga’s Old Town, notable as one of the few remaining medieval entrances to the former fortified city.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Swedish Gate
Target entity description: Swedish Gate is a historic city gate in Riga’s Old Town, notable as one of the few remaining medieval entrances to the former fortified city.
  • A. Norway Gate
    Norway Gate is a historic entrance structure associated with the Kastellet fortress complex.
  • B. Musegg Gate
    Musegg Gate is one of the historic towers and entrances incorporated into Lucerne’s medieval Musegg Wall fortifications in Switzerland.
  • C. Narva Gate
    Narva Gate is a historic triumphal arch in Saint Petersburg, Russia, commemorating Russian military victories and serving as a notable architectural landmark.
  • D. Londorossi Gate
    Londorossi Gate is a primary western entrance and registration point to Mount Kilimanjaro National Park, commonly used by climbers beginning the Lemosho Route.
  • E. Erer Gate
    Erer Gate is one of the historic gateways in the ancient walled city of Harar Jugol in eastern Ethiopia.
  • 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_69d88395e6c88190b22730f335107c14 completed April 10, 2026, 4:59 a.m.
NER Named-entity recognition batch_69e3b50983148190a116f7e7017ccb1c completed April 18, 2026, 4:44 p.m.
NED1 Entity disambiguation (via context triple) batch_6a00c2a929b081909d3a5a680ae93a78 completed May 10, 2026, 5:38 p.m.
NEDg Description generation batch_6a00c355f4108190a4209599bf5f50da completed May 10, 2026, 5:41 p.m.
NED2 Entity disambiguation (via description) batch_6a00c413314881909e308588af09ce2a completed May 10, 2026, 5:44 p.m.
Created at: April 10, 2026, 5:24 a.m.