Triple

T20516393
Position Surface form Disambiguated ID Type / Status
Subject Marienplatz E503692 entity
Predicate connectsWith P37 FINISHED
Object Tal
Tal is a historic street in Munich’s Old Town that runs east from Marienplatz toward Isartor, lined with shops, restaurants, and notable traditional buildings.
 E1435866 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: Tal | Statement: [Marienplatz, connectsWith, Tal]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Tal
Context triple: [Marienplatz, connectsWith, Tal]
  • A. Tal
    Tal is a common Latvian and Jewish surname most famously borne by Mikhail Tal, the eighth World Chess Champion renowned for his brilliant attacking style.
  • B. Talho
    Talho is a settlement located within the municipality of Ribeira Brava in Cape Verde.
  • C. Tal R
    Tal R is a contemporary Danish-Israeli artist known for his vibrant, expressive paintings and eclectic, symbol-laden imagery.
  • D. Talke
    Talke is a village and suburb in Staffordshire, England, situated near the town of Kidsgrove.
  • E. Talange
    Talange is a small commune in northeastern France’s Moselle department, known for its location in the industrial Moselle valley between Metz and Thionville.
  • 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: Tal
Triple: [Marienplatz, connectsWith, Tal]
Generated description
Tal is a historic street in Munich’s Old Town that runs east from Marienplatz toward Isartor, lined with shops, restaurants, and notable traditional buildings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Tal
Target entity description: Tal is a historic street in Munich’s Old Town that runs east from Marienplatz toward Isartor, lined with shops, restaurants, and notable traditional buildings.
  • A. Tal
    Tal is a common Latvian and Jewish surname most famously borne by Mikhail Tal, the eighth World Chess Champion renowned for his brilliant attacking style.
  • B. Talho
    Talho is a settlement located within the municipality of Ribeira Brava in Cape Verde.
  • C. Tal R
    Tal R is a contemporary Danish-Israeli artist known for his vibrant, expressive paintings and eclectic, symbol-laden imagery.
  • D. Talke
    Talke is a village and suburb in Staffordshire, England, situated near the town of Kidsgrove.
  • E. Talange
    Talange is a small commune in northeastern France’s Moselle department, known for its location in the industrial Moselle valley between Metz and Thionville.
  • 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_69e0b4b2aa788190ae9eb37c1d73b1f1 completed April 16, 2026, 10:06 a.m.
NER Named-entity recognition batch_69e69f41eee481908121e54c7bd691ca completed April 20, 2026, 9:48 p.m.
NED1 Entity disambiguation (via context triple) batch_6a089d3b73f88190bd5a68d6a1056df5 completed May 16, 2026, 4:37 p.m.
NEDg Description generation batch_6a089df251c481908043e3d7ad79198f completed May 16, 2026, 4:40 p.m.
NED2 Entity disambiguation (via description) batch_6a089e8a05488190b3470f4ffb5927ce completed May 16, 2026, 4:42 p.m.
Created at: April 16, 2026, 11:36 a.m.