Triple

T15912995
Position Surface form Disambiguated ID Type / Status
Subject Midilli E385894 entity
Predicate formerName P65 FINISHED
Object Breslau
Breslau is the former German name for the city now known as Wrocław in southwestern Poland, a historic cultural and economic center of Silesia.
 E238097 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: Breslau | Statement: [Midilli, formerName, Breslau]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Breslau
Context triple: [Midilli, formerName, Breslau]
  • A. Breslau
    Breslau is the historical German name for the city now known as Wrocław in southwestern Poland, a major cultural and academic center in Central Europe.
  • B. Stettin
    Stettin, now known as Szczecin, is a major port city on the Oder River in northwestern Poland near the Baltic Sea.
  • C. Glogau
    Glogau is the German name for the town of Głogów, a historic city in southwestern Poland on the Oder River.
  • D. Oppeln
    Oppeln is the historical German name for the city of Opole, a major cultural and administrative center in southwestern Poland’s Silesia region.
  • E. Lemberg
    Lemberg is a small commune in northeastern France’s Moselle department, situated in the forested, hilly region known as the Pays de Bitche near the German 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: Breslau
Triple: [Midilli, formerName, Breslau]
Generated description
Breslau is the former German name for the city now known as Wrocław in southwestern Poland, a historic cultural and economic center of Silesia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Breslau
Target entity description: Breslau is the former German name for the city now known as Wrocław in southwestern Poland, a historic cultural and economic center of Silesia.
  • A. Breslau chosen
    Breslau is the historical German name for the city now known as Wrocław in southwestern Poland, a major cultural and academic center in Central Europe.
  • B. Stettin
    Stettin, now known as Szczecin, is a major port city on the Oder River in northwestern Poland near the Baltic Sea.
  • C. Glogau
    Glogau is the German name for the town of Głogów, a historic city in southwestern Poland on the Oder River.
  • D. Oppeln
    Oppeln is the historical German name for the city of Opole, a major cultural and administrative center in southwestern Poland’s Silesia region.
  • E. Lemberg
    Lemberg is a small commune in northeastern France’s Moselle department, situated in the forested, hilly region known as the Pays de Bitche near the German border.
  • F. None of above.

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_69d86da686e4819097cbf3b1fc2d881d completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e156601c988190b9bd0cd75897651b completed April 16, 2026, 9:36 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffb5a5b0dc81909606d667c3bc0edf completed May 9, 2026, 10:31 p.m.
NEDg Description generation batch_69ffb663ac1c8190a7def27579acf8aa completed May 9, 2026, 10:34 p.m.
NED2 Entity disambiguation (via description) batch_69ffb6b9007c819096a02c416239dcac completed May 9, 2026, 10:35 p.m.
Created at: April 10, 2026, 4:52 a.m.