Triple

T21111791
Position Surface form Disambiguated ID Type / Status
Subject Marshall of Cambridge E520188 entity
Predicate abbreviation P43 FINISHED
Object Marshall
Marshall is a British aerospace and defense company known for aircraft maintenance, modification, and engineering services.
 E1467950 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: Marshall | Statement: [Marshall of Cambridge, abbreviation, Marshall]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Marshall
Context triple: [Marshall of Cambridge, abbreviation, Marshall]
  • A. Marshall
    Marshall is a 2017 biographical legal drama film about a young Thurgood Marshall, directed by Reginald Hudlin and starring Chadwick Boseman.
  • B. Marshall
    Marshall is a common English surname borne by numerous notable figures, including military leaders, politicians, and artists.
  • C. Marshall
    Marshall is a small East Texas city known for its historic architecture, role in the Civil War era, and cultural institutions such as Wiley College.
  • D. Marshall
    Marshall is one of the Adirondack High Peaks in New York’s Adirondack Mountains, known for its remote location and challenging, often trailless ascent.
  • E. Marshall
    Marshall is a masculine given name of English origin commonly used in the United States and other English-speaking countries.
  • 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: Marshall
Triple: [Marshall of Cambridge, abbreviation, Marshall]
Generated description
Marshall is a British aerospace and defense company known for aircraft maintenance, modification, and engineering services.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Marshall
Target entity description: Marshall is a British aerospace and defense company known for aircraft maintenance, modification, and engineering services.
  • A. Marshall
    Marshall is a common English surname borne by numerous notable figures, including military leaders, politicians, and artists.
  • B. Marshall
    Marshall is a masculine given name of English origin commonly used in the United States and other English-speaking countries.
  • C. Marshall
    Marshall is a small East Texas city known for its historic architecture, role in the Civil War era, and cultural institutions such as Wiley College.
  • D. Marshall
    Marshall is one of the Adirondack High Peaks in New York’s Adirondack Mountains, known for its remote location and challenging, often trailless ascent.
  • E. Marshall
    Marshall is the college football team representing Marshall University, competing in NCAA Division I as the Thundering Herd.
  • 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_69e0b509a318819092fbbcb21d1fe603 completed April 16, 2026, 10:08 a.m.
NER Named-entity recognition batch_69e72102d99c8190a1ea5a6981da6da0 completed April 21, 2026, 7:02 a.m.
NED1 Entity disambiguation (via context triple) batch_6a0965e013388190a058d84063e22694 completed May 17, 2026, 6:53 a.m.
NEDg Description generation batch_6a09670987f0819086b021581db69c85 completed May 17, 2026, 6:58 a.m.
NED2 Entity disambiguation (via description) batch_6a0967cefab08190b01e2c897f081105 completed May 17, 2026, 7:01 a.m.
Created at: April 16, 2026, 2:54 p.m.