Triple

T17398684
Position Surface form Disambiguated ID Type / Status
Subject Lord Paul of Marylebone E423023 entity
Predicate hasFamilyName P18 FINISHED
Object Paul
Paul is a British industrialist and Labour politician who was granted a life peerage as Lord Paul of Marylebone.
E1266831 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: Paul | Statement: [Lord Paul of Marylebone, hasFamilyName, Paul]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Paul
Context triple: [Lord Paul of Marylebone, hasFamilyName, Paul]
  • A. Paul
    Paul is a laid-back, charming sperm donor whose unexpected involvement with his biological children disrupts a lesbian couple’s family dynamic in the film "The Kids Are All Right."
  • B. Paul
    Paul is a 2011 sci-fi comedy film about two British geeks who encounter a wisecracking alien during a road trip across the United States.
  • C. Paul
    Paul is a village and civil parish in Cornwall, England, known for its historic church and coastal setting near Penzance.
  • D. Paul
    Paul is a character from the "Wild" universe, known for his role within its adventurous, nature-centered narrative.
  • E. Paul
    Paul is a character from the film "Nobody’s Business," contributing to the story’s exploration of personal and family relationships.
  • 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: Paul
Triple: [Lord Paul of Marylebone, hasFamilyName, Paul]
Generated description
Paul is a British industrialist and Labour politician who was granted a life peerage as Lord Paul of Marylebone.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Paul
Target entity description: Paul is a British industrialist and Labour politician who was granted a life peerage as Lord Paul of Marylebone.
  • A. Paul
    Paul is a family name most notably borne by Wolfgang Paul, the German physicist and Nobel laureate in Physics.
  • B. Paul
    Paul is a village and civil parish in Cornwall, England, known for its historic church and coastal setting near Penzance.
  • C. Paul
    Paul is an early Christian apostle and missionary whose letters form a significant portion of the New Testament and profoundly shaped Christian theology.
  • D. Paul
    Paul is a central early Christian apostle and missionary, traditionally credited with writing many New Testament letters and shaping much of Christian theology.
  • E. Paul
    Paul is a masculine given name of Latin origin, widely used in many Western and Christian-influenced cultures.
  • 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_69d889d710288190bf0f4762801fefae completed April 10, 2026, 5:25 a.m.
NER Named-entity recognition batch_69e43abf7ea08190a9d9f9358e3bb684 completed April 19, 2026, 2:15 a.m.
NED1 Entity disambiguation (via context triple) batch_6a01a002b034819099fd74e01bb382b0 completed May 11, 2026, 9:23 a.m.
NEDg Description generation batch_6a01a176d2488190951bbe07233a37e4 completed May 11, 2026, 9:29 a.m.
NED2 Entity disambiguation (via description) batch_6a01a58b12088190828078c69c4fff4b completed May 11, 2026, 9:46 a.m.
Created at: April 10, 2026, 5:45 a.m.