Triple

T19082956
Position Surface form Disambiguated ID Type / Status
Subject Ravad E467074 entity
Predicate alsoKnownAs P39 FINISHED
Object Rabad
Rabad is a medieval Jewish rabbi and Talmudic scholar, best known for his critical glosses on Maimonides’ Mishneh Torah.
 E1356844 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: Rabad | Statement: [Ravad, alsoKnownAs, Rabad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Rabad
Context triple: [Ravad, alsoKnownAs, Rabad]
  • A. Ajdal
    Ajdal was a top-class British-trained Thoroughbred racehorse of the 1980s, best known as a champion sprinter and miler.
  • B. Rutba
    Rutba is a remote desert town in western Iraq that serves as a key transit point on the highway linking Baghdad with Jordan and Syria.
  • C. Balanjar
    Balanjar was an early medieval city in the North Caucasus that served as one of the principal political and military centers of the Khazar Khaganate.
  • D. Bazarduzu
    Bazarduzu is the highest mountain in Azerbaijan, located in the Greater Caucasus range on the border with Russia.
  • E. Cabadbaran
    Cabadbaran is a component city in the Caraga region of the Philippines, serving as the capital of the province of Agusan del Norte.
  • 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: Rabad
Triple: [Ravad, alsoKnownAs, Rabad]
Generated description
Rabad is a medieval Jewish rabbi and Talmudic scholar, best known for his critical glosses on Maimonides’ Mishneh Torah.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Rabad
Target entity description: Rabad is a medieval Jewish rabbi and Talmudic scholar, best known for his critical glosses on Maimonides’ Mishneh Torah.
  • A. Ajdal
    Ajdal was a top-class British-trained Thoroughbred racehorse of the 1980s, best known as a champion sprinter and miler.
  • B. Rutba
    Rutba is a remote desert town in western Iraq that serves as a key transit point on the highway linking Baghdad with Jordan and Syria.
  • C. Balanjar
    Balanjar was an early medieval city in the North Caucasus that served as one of the principal political and military centers of the Khazar Khaganate.
  • D. Bazarduzu
    Bazarduzu is the highest mountain in Azerbaijan, located in the Greater Caucasus range on the border with Russia.
  • E. Cabadbaran
    Cabadbaran is a component city in the Caraga region of the Philippines, serving as the capital of the province of Agusan del Norte.
  • 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_69d8dd04f4488190b1121cc53ef2bfd6 completed April 10, 2026, 11:20 a.m.
NER Named-entity recognition batch_69e5e2eab58c8190a987c88d633c92ec completed April 20, 2026, 8:25 a.m.
NED1 Entity disambiguation (via context triple) batch_6a05d3663f748190bec29d54c6b86277 completed May 14, 2026, 1:51 p.m.
NEDg Description generation batch_6a05d3fe45c881908622e745b66abfd2 completed May 14, 2026, 1:54 p.m.
NED2 Entity disambiguation (via description) batch_6a05d4b2292c8190bd4cd73969c610d8 completed May 14, 2026, 1:57 p.m.
Created at: April 10, 2026, 12:04 p.m.