Triple

T2254991
Position Surface form Disambiguated ID Type / Status
Subject Surah Al-Qamar E49700 entity
Predicate mentionsPeople P831 FINISHED
Object ‘Ad
‘Ad is an ancient Arabian tribe mentioned in the Qur’an for their power, prosperity, and subsequent destruction after rejecting the message of the prophet Hud.
 E249005 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: ‘Ad | Statement: [Surah Al-Qamar, mentionsPeople, ‘Ad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: ‘Ad
Context triple: [Surah Al-Qamar, mentionsPeople, ‘Ad]
  • A. .ad
    .ad is the country code top-level domain (ccTLD) assigned to the Principality of Andorra for use in internet addresses.
  • B. AD
    AD is a CERN facility that slows down antiprotons so they can be used in precision experiments studying antimatter.
  • C. AdE
    AdE is the abbreviation for the Akademio de Esperanto, the language-regulating body that oversees the evolution and norms of Esperanto.
  • D. ARE
    ARE is a professional licensure examination for architects in the United States that assesses candidates’ knowledge and skills required for independent practice.
  • E. DA
    DA is a postcode area in southeast England covering parts of south-east London and northwest Kent, including towns such as Dartford and Sidcup.
  • 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: ‘Ad
Triple: [Surah Al-Qamar, mentionsPeople, ‘Ad]
Generated description
‘Ad is an ancient Arabian tribe mentioned in the Qur’an for their power, prosperity, and subsequent destruction after rejecting the message of the prophet Hud.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: ‘Ad
Target entity description: ‘Ad is an ancient Arabian tribe mentioned in the Qur’an for their power, prosperity, and subsequent destruction after rejecting the message of the prophet Hud.
  • A. .ad
    .ad is the country code top-level domain (ccTLD) assigned to the Principality of Andorra for use in internet addresses.
  • B. AD
    AD is a CERN facility that slows down antiprotons so they can be used in precision experiments studying antimatter.
  • C. AdE
    AdE is the abbreviation for the Akademio de Esperanto, the language-regulating body that oversees the evolution and norms of Esperanto.
  • D. ARE
    ARE is a professional licensure examination for architects in the United States that assesses candidates’ knowledge and skills required for independent practice.
  • E. DA
    DA is a postcode area in southeast England covering parts of south-east London and northwest Kent, including towns such as Dartford and Sidcup.
  • 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_69a88aaa9250819095e127d0d77e8a32 completed March 4, 2026, 7:40 p.m.
NER Named-entity recognition batch_69abc121af78819085b2e601d2f9bcdf completed March 7, 2026, 6:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae6b1fc8808190aebc534ea5adb534 completed March 9, 2026, 6:39 a.m.
NEDg Description generation batch_69ae6c87e3108190bc3852b3ebdba45a completed March 9, 2026, 6:45 a.m.
NED2 Entity disambiguation (via description) batch_69ae6d0f723c8190bf0f91dad961e377 completed March 9, 2026, 6:47 a.m.
Created at: March 4, 2026, 7:47 p.m.