Triple

T22888781
Position Surface form Disambiguated ID Type / Status
Subject Jewish Historical Institute in Warsaw E567676 entity
Predicate shortName P43 FINISHED
Object ŻIH
ŻIH is the commonly used abbreviation for the Jewish Historical Institute in Warsaw, a major center for research, documentation, and preservation of Jewish history and culture in Poland.
 E1560743 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: ŻIH | Statement: [Jewish Historical Institute in Warsaw, shortName, ŻIH]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ŻIH
Context triple: [Jewish Historical Institute in Warsaw, shortName, ŻIH]
  • A. ZI
    ZI is the vehicle registration code used on license plates for vehicles registered in the district of Görlitz in Germany.
  • B. Zai
    Zai is the given name of Zhang Zai, an influential 11th-century Chinese Neo-Confucian philosopher.
  • C. Zi
    Zi is the ancestral clan name of the royal family that founded and ruled China’s Shang dynasty.
  • D. Ziu
    Ziu is the Old High German name for the Germanic god of war and the sky, cognate with the Norse deity Týr.
  • E. Zihuan
    Zihuan is the courtesy name of Cao Pi, the first emperor of the state of Cao Wei during China’s Three Kingdoms period.
  • 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: ŻIH
Triple: [Jewish Historical Institute in Warsaw, shortName, ŻIH]
Generated description
ŻIH is the commonly used abbreviation for the Jewish Historical Institute in Warsaw, a major center for research, documentation, and preservation of Jewish history and culture in Poland.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ŻIH
Target entity description: ŻIH is the commonly used abbreviation for the Jewish Historical Institute in Warsaw, a major center for research, documentation, and preservation of Jewish history and culture in Poland.
  • A. ZI
    ZI is the vehicle registration code used on license plates for vehicles registered in the district of Görlitz in Germany.
  • B. Zai
    Zai is the given name of Zhang Zai, an influential 11th-century Chinese Neo-Confucian philosopher.
  • C. Zi
    Zi is the ancestral clan name of the royal family that founded and ruled China’s Shang dynasty.
  • D. Ziu
    Ziu is the Old High German name for the Germanic god of war and the sky, cognate with the Norse deity Týr.
  • E. Zihuan
    Zihuan is the courtesy name of Cao Pi, the first emperor of the state of Cao Wei during China’s Three Kingdoms period.
  • 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_69e2458a92ec81908fc1cd5f6407d2ab completed April 17, 2026, 2:36 p.m.
NER Named-entity recognition batch_69f17fc37a448190996e106aacc900f4 completed April 29, 2026, 3:49 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0bb9be4c688190820b484bea11696b completed May 19, 2026, 1:15 a.m.
NEDg Description generation batch_6a0bbb38da508190bc1d9bc8538cdbe2 completed May 19, 2026, 1:22 a.m.
NED2 Entity disambiguation (via description) batch_6a0bbc2a2244819090ead891e1a866ed completed May 19, 2026, 1:26 a.m.
Created at: April 17, 2026, 3:40 p.m.