Triple

T14771767
Position Surface form Disambiguated ID Type / Status
Subject Angels E347150 entity
Predicate include P1393 FINISHED
Object Munkar
Munkar is an Islamic angel known, along with his counterpart Nakir, for questioning the dead in their graves about their faith and deeds.
 E1118291 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: Munkar | Statement: [Angels, include, Munkar]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Munkar
Context triple: [Angels, include, Munkar]
  • A. Hamutal
    Hamutal was a queen of Judah, known as the mother of the last king of Judah, Zedekiah, during the final years before the Babylonian exile.
  • B. Muanisolo
    Muanisolo is a village located on Kadavu Island in Fiji, known for its traditional Fijian rural lifestyle and coastal setting.
  • C. Mandark
    Mandark is the villainous boy genius and rival scientist to Dexter in the animated television series "Dexter's Laboratory."
  • D. Malakili
    Malakili is the human beastmaster in Star Wars: Return of the Jedi who tends and grows emotionally attached to Jabba the Hutt’s rancor.
  • E. Mardik
    Mardik is the given name of Mardik Martin, an American screenwriter known for his collaborations with director Martin Scorsese.
  • 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: Munkar
Triple: [Angels, include, Munkar]
Generated description
Munkar is an Islamic angel known, along with his counterpart Nakir, for questioning the dead in their graves about their faith and deeds.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Munkar
Target entity description: Munkar is an Islamic angel known, along with his counterpart Nakir, for questioning the dead in their graves about their faith and deeds.
  • A. Hamutal
    Hamutal was a queen of Judah, known as the mother of the last king of Judah, Zedekiah, during the final years before the Babylonian exile.
  • B. Muanisolo
    Muanisolo is a village located on Kadavu Island in Fiji, known for its traditional Fijian rural lifestyle and coastal setting.
  • C. Mandark
    Mandark is the villainous boy genius and rival scientist to Dexter in the animated television series "Dexter's Laboratory."
  • D. Malakili
    Malakili is the human beastmaster in Star Wars: Return of the Jedi who tends and grows emotionally attached to Jabba the Hutt’s rancor.
  • E. Mardik
    Mardik is the given name of Mardik Martin, an American screenwriter known for his collaborations with director Martin Scorsese.
  • 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_69d822e8896c819091169882f9b20486 completed April 9, 2026, 10:06 p.m.
NER Named-entity recognition batch_69dec81334e08190a77d760e507d00ed completed April 14, 2026, 11:04 p.m.
NED1 Entity disambiguation (via context triple) batch_69fe0cfabdfc8190ae7ee06b11f9b540 completed May 8, 2026, 4:19 p.m.
NEDg Description generation batch_69fe1344428081908948ad757ffec451 completed May 8, 2026, 4:45 p.m.
NED2 Entity disambiguation (via description) batch_69fe142e5030819081bfe87d5d7b6581 completed May 8, 2026, 4:49 p.m.
Created at: April 10, 2026, 1:31 a.m.