Triple

T18551355
Position Surface form Disambiguated ID Type / Status
Subject Kārlis Zāle E453386 entity
Predicate familyName P18 FINISHED
Object Zāle
Zāle is the surname of Kārlis Zāle, a notable Latvian sculptor and monument designer.
 E1330032 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: Zāle | Statement: [Kārlis Zāle, familyName, Zāle]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Zāle
Context triple: [Kārlis Zāle, familyName, Zāle]
  • A. Zalba
    Zalba is a locality situated within Tunisia’s Mahdia Governorate, a coastal region in the east-central part of the country.
  • B. Zare
    Zare is the surname of Richard N. Zare, a prominent American chemist known for his pioneering work in laser chemistry and molecular reaction dynamics.
  • C. Zau
    Zau is an ancient city, historically known as Sais, that served as an important religious and political center in Egypt’s Nile Delta.
  • D. Zemba
    Zemba is a Bantu language variety spoken primarily in southwestern Angola and northern Namibia, closely related to and often considered a dialect of Herero.
  • E. Kleiza
    Kleiza is the surname of Lithuanian former professional basketball player Linas Kleiza, who played in the NBA and for top European clubs.
  • 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: Zāle
Triple: [Kārlis Zāle, familyName, Zāle]
Generated description
Zāle is the surname of Kārlis Zāle, a notable Latvian sculptor and monument designer.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Zāle
Target entity description: Zāle is the surname of Kārlis Zāle, a notable Latvian sculptor and monument designer.
  • A. Zalba
    Zalba is a locality situated within Tunisia’s Mahdia Governorate, a coastal region in the east-central part of the country.
  • B. Zare
    Zare is the surname of Richard N. Zare, a prominent American chemist known for his pioneering work in laser chemistry and molecular reaction dynamics.
  • C. Zau
    Zau is an ancient city, historically known as Sais, that served as an important religious and political center in Egypt’s Nile Delta.
  • D. Zemba
    Zemba is a Bantu language variety spoken primarily in southwestern Angola and northern Namibia, closely related to and often considered a dialect of Herero.
  • E. Kleiza
    Kleiza is the surname of Lithuanian former professional basketball player Linas Kleiza, who played in the NBA and for top European clubs.
  • 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_69d8d388b0c881908e610a1c45b52640 completed April 10, 2026, 10:40 a.m.
NER Named-entity recognition batch_69e53800c0fc819097782f1e81574598 completed April 19, 2026, 8:16 p.m.
NED1 Entity disambiguation (via context triple) batch_6a049adfedf4819094904078d0707fec completed May 13, 2026, 3:38 p.m.
NEDg Description generation batch_6a049c355cb08190a63addeba8293e5c completed May 13, 2026, 3:43 p.m.
NED2 Entity disambiguation (via description) batch_6a049cfa32588190a6e4abf128aced0a completed May 13, 2026, 3:47 p.m.
Created at: April 10, 2026, 11:38 a.m.