Triple

T7763764
Position Surface form Disambiguated ID Type / Status
Subject Yemeni Air Force E176091 entity
Predicate operatesAirbasesIn P78557 FINISHED
Object Al Anad
Al Anad is a major military airbase in southern Yemen that has served as a strategic hub for air operations and international military cooperation.
 E687669 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: Al Anad | Statement: [Yemeni Air Force, operatesAirbasesIn, Al Anad]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Al Anad
Context triple: [Yemeni Air Force, operatesAirbasesIn, Al Anad]
  • A. Al Mokawloon
    Al Mokawloon is an Egyptian football club known for developing talented players, including international star Mohamed Salah.
  • B. Al Mandaq
    Al Mandaq is a town in southwestern Saudi Arabia known for its mountainous terrain and cool climate within the Al Bahah region.
  • C. Al-Masad
    Al-Masad is the 111th chapter of the Qur’an, known for condemning Abu Lahab and his wife for their opposition to the Prophet Muhammad.
  • D. Ad-Duha
    Ad-Duha is the 93rd chapter of the Qur’an, known for consoling the Prophet Muhammad and affirming that God’s care and future blessings surpass past hardships.
  • E. Al-Ashbah wa al-Naza'ir
    Al-Ashbah wa al-Naza'ir is a seminal work of Islamic legal theory that systematically presents and analyzes legal maxims and analogous cases within the Shafi'i school of jurisprudence.
  • 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: Al Anad
Triple: [Yemeni Air Force, operatesAirbasesIn, Al Anad]
Generated description
Al Anad is a major military airbase in southern Yemen that has served as a strategic hub for air operations and international military cooperation.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Al Anad
Target entity description: Al Anad is a major military airbase in southern Yemen that has served as a strategic hub for air operations and international military cooperation.
  • A. Al Mokawloon
    Al Mokawloon is an Egyptian football club known for developing talented players, including international star Mohamed Salah.
  • B. Al Mandaq
    Al Mandaq is a town in southwestern Saudi Arabia known for its mountainous terrain and cool climate within the Al Bahah region.
  • C. Al-Masad
    Al-Masad is the 111th chapter of the Qur’an, known for condemning Abu Lahab and his wife for their opposition to the Prophet Muhammad.
  • D. Ad-Duha
    Ad-Duha is the 93rd chapter of the Qur’an, known for consoling the Prophet Muhammad and affirming that God’s care and future blessings surpass past hardships.
  • E. Al-Ashbah wa al-Naza'ir
    Al-Ashbah wa al-Naza'ir is a seminal work of Islamic legal theory that systematically presents and analyzes legal maxims and analogous cases within the Shafi'i school of jurisprudence.
  • 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_69c69962923c8190ac74d28b4f9fe0a0 completed March 27, 2026, 2:51 p.m.
NER Named-entity recognition batch_69c708b13c688190839c920ec196cada completed March 27, 2026, 10:46 p.m.
NED1 Entity disambiguation (via context triple) batch_69c8c7da8b848190b378f694118dfa19 completed March 29, 2026, 6:34 a.m.
NEDg Description generation batch_69c8c8d7a51481908fd537dbb57a6116 completed March 29, 2026, 6:38 a.m.
NED2 Entity disambiguation (via description) batch_69c8c98179908190a68b7f029fff8e3c completed March 29, 2026, 6:41 a.m.
Created at: March 27, 2026, 4:09 p.m.