Triple

T4362564
Position Surface form Disambiguated ID Type / Status
Subject The Graphic E98693 entity
Predicate employed P7 FINISHED
Object Charles Green
Charles Green was a British illustrator known for his detailed work in Victorian periodicals and book illustrations.
 E434367 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: Charles Green | Statement: [The Graphic, employed, Charles Green]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Charles Green
Context triple: [The Graphic, employed, Charles Green]
  • A. Charles Green
    Charles Green was an 18th-century English astronomer who sailed with Captain James Cook to observe the 1769 transit of Venus and conduct astronomical measurements.
  • B. Charles Green
    Charles Green was an Anglican clergyman who became a prominent Welsh bishop and later Archbishop of Wales in the mid-20th century.
  • C. Charles Foster
    Charles Foster is one of the children of acclaimed American actress and filmmaker Jodie Foster.
  • D. Richard Ellis
    Richard Ellis was a 19th-century Texas statesman best known for presiding over the convention that declared Texas’ independence from Mexico.
  • E. Paul Wilson
    Paul Wilson is a Scottish musician best known as the bassist for the alternative rock band Snow Patrol.
  • 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: Charles Green
Triple: [The Graphic, employed, Charles Green]
Generated description
Charles Green was a British illustrator known for his detailed work in Victorian periodicals and book illustrations.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Charles Green
Target entity description: Charles Green was a British illustrator known for his detailed work in Victorian periodicals and book illustrations.
  • A. Charles Green
    Charles Green was an 18th-century English astronomer who sailed with Captain James Cook to observe the 1769 transit of Venus and conduct astronomical measurements.
  • B. Charles Green
    Charles Green was an Anglican clergyman who became a prominent Welsh bishop and later Archbishop of Wales in the mid-20th century.
  • C. Charles Foster
    Charles Foster is one of the children of acclaimed American actress and filmmaker Jodie Foster.
  • D. Richard Ellis
    Richard Ellis was a 19th-century Texas statesman best known for presiding over the convention that declared Texas’ independence from Mexico.
  • E. Paul Wilson
    Paul Wilson is a Scottish musician best known as the bassist for the alternative rock band Snow Patrol.
  • 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_69b3454c772081908e20173e379e8ebe completed March 12, 2026, 10:59 p.m.
NER Named-entity recognition batch_69b351e5ee308190a9271e73689b4a2b completed March 12, 2026, 11:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5dbc68534819095ce62645ca79eff completed March 14, 2026, 10:05 p.m.
NEDg Description generation batch_69b5df8336e881908c875b8411c2fe4d completed March 14, 2026, 10:21 p.m.
NED2 Entity disambiguation (via description) batch_69b5e0ded0288190b615364e9ae10821 completed March 14, 2026, 10:27 p.m.
Created at: March 12, 2026, 11:16 p.m.