Triple

T3759792
Position Surface form Disambiguated ID Type / Status
Subject Amal Clooney E82132 entity
Predicate familyName P18 FINISHED
Object Alamuddin
Alamuddin is the Lebanese Druze family name of prominent human rights lawyer Amal Clooney (née Amal Alamuddin).
E422729 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: Alamuddin | Statement: [Amal Clooney, familyName, Alamuddin]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Alamuddin
Context triple: [Amal Clooney, familyName, Alamuddin]
  • A. Shuja-ud-Din Muhammad Khan
    Shuja-ud-Din Muhammad Khan was an 18th-century Nawab of Bengal known for his relatively stable and prosperous rule before the rise of Alivardi Khan.
  • B. Najm-ud-Daulah
    Najm-ud-Daulah was an 18th-century Nawab of Bengal who succeeded his father Mir Jafar under the dominance of the British East India Company.
  • C. Shams-ud-Dīn
    Shams-ud-Dīn is the formal given name of the famed 14th-century Persian lyric poet Hafez of Shiraz.
  • D. Raja Zulqarnain Khan
    Raja Zulqarnain Khan is a Pakistani politician who served as the President of Azad Jammu and Kashmir.
  • E. Nur-ud-din Muhammad Salim
    Nur-ud-din Muhammad Salim, better known by his regnal name Jahangir, was the fourth Mughal emperor of India, renowned for his patronage of the arts and relatively liberal, if often indulgent, rule in the early 17th century.
  • 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: Alamuddin
Triple: [Amal Clooney, familyName, Alamuddin]
Generated description
Alamuddin is the Lebanese Druze family name of prominent human rights lawyer Amal Clooney (née Amal Alamuddin).
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Alamuddin
Target entity description: Alamuddin is the Lebanese Druze family name of prominent human rights lawyer Amal Clooney (née Amal Alamuddin).
  • A. Shuja-ud-Din Muhammad Khan
    Shuja-ud-Din Muhammad Khan was an 18th-century Nawab of Bengal known for his relatively stable and prosperous rule before the rise of Alivardi Khan.
  • B. Najm-ud-Daulah
    Najm-ud-Daulah was an 18th-century Nawab of Bengal who succeeded his father Mir Jafar under the dominance of the British East India Company.
  • C. Shams-ud-Dīn
    Shams-ud-Dīn is the formal given name of the famed 14th-century Persian lyric poet Hafez of Shiraz.
  • D. Raja Zulqarnain Khan
    Raja Zulqarnain Khan is a Pakistani politician who served as the President of Azad Jammu and Kashmir.
  • E. Nur-ud-din Muhammad Salim
    Nur-ud-din Muhammad Salim, better known by his regnal name Jahangir, was the fourth Mughal emperor of India, renowned for his patronage of the arts and relatively liberal, if often indulgent, rule in the early 17th century.
  • 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_69ad8b1db40081908b61ffa6b78afd4d completed March 8, 2026, 2:43 p.m.
NER Named-entity recognition batch_69adcbc3d3f48190974cec104080949f completed March 8, 2026, 7:19 p.m.
NED1 Entity disambiguation (via context triple) batch_69b595eea03c8190a76a4e09a6d03919 completed March 14, 2026, 5:07 p.m.
NEDg Description generation batch_69b599c94ce48190a77065377e7c09f3 completed March 14, 2026, 5:24 p.m.
NED2 Entity disambiguation (via description) batch_69b59a2683488190954d95bc2f2bf456 completed March 14, 2026, 5:25 p.m.
Created at: March 8, 2026, 3:35 p.m.