Triple

T15992012
Position Surface form Disambiguated ID Type / Status
Subject Roger Allam E387855 entity
Predicate familyName P18 FINISHED
Object Allam
Allam is a surname of Arabic origin borne by various notable individuals across fields such as acting, politics, and academia.
 E1187285 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: Allam | Statement: [Roger Allam, familyName, Allam]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Allam
Context triple: [Roger Allam, familyName, Allam]
  • A. Alladi
    Alladi is an Indian surname notably associated with the distinguished jurist and constitutional expert Alladi Krishnaswamy Iyer.
  • B. Alimin
    Alimin was an early 20th-century Indonesian communist leader and activist who played a key role in the formation of the country’s communist movement.
  • C. Asalluhi
    Asalluhi is a Mesopotamian god associated with incantations, healing, and exorcism, often linked to the later Babylonian deity Marduk.
  • D. Amlash
    Amlash is a city in northern Iran known for its location in the lush, Caspian coastal region of Gilan Province.
  • E. Asmal
    Asmal is a surname most notably associated with Kader Asmal, a prominent South African anti-apartheid activist, academic, and government minister.
  • 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: Allam
Triple: [Roger Allam, familyName, Allam]
Generated description
Allam is a surname of Arabic origin borne by various notable individuals across fields such as acting, politics, and academia.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Allam
Target entity description: Allam is a surname of Arabic origin borne by various notable individuals across fields such as acting, politics, and academia.
  • A. Alladi
    Alladi is an Indian surname notably associated with the distinguished jurist and constitutional expert Alladi Krishnaswamy Iyer.
  • B. Alimin
    Alimin was an early 20th-century Indonesian communist leader and activist who played a key role in the formation of the country’s communist movement.
  • C. Asalluhi
    Asalluhi is a Mesopotamian god associated with incantations, healing, and exorcism, often linked to the later Babylonian deity Marduk.
  • D. Amlash
    Amlash is a city in northern Iran known for its location in the lush, Caspian coastal region of Gilan Province.
  • E. Asmal
    Asmal is a surname most notably associated with Kader Asmal, a prominent South African anti-apartheid activist, academic, and government minister.
  • 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_69d86daa562c81908aacc179c0fe8fb5 completed April 10, 2026, 3:25 a.m.
NER Named-entity recognition batch_69e157844ed881908b42bfc1bb740d4e completed April 16, 2026, 9:41 p.m.
NED1 Entity disambiguation (via context triple) batch_69ffc3d3ef2881909213ff608192f1ef completed May 9, 2026, 11:31 p.m.
NEDg Description generation batch_69ffc47bce748190a651fff307aad88d completed May 9, 2026, 11:34 p.m.
NED2 Entity disambiguation (via description) batch_69ffc4e14e1881909210a78426546e88 completed May 9, 2026, 11:36 p.m.
Created at: April 10, 2026, 4:54 a.m.