Triple

T588402
Position Surface form Disambiguated ID Type / Status
Subject Julian Amery E17211 entity
Predicate familyName P18 FINISHED
Object Amery
Amery is an English surname most notably associated with a British political family, including Conservative politician Julian Amery.
 E75162 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: Amery | Statement: [Julian Amery, familyName, Amery]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Amery
Context triple: [Julian Amery, familyName, Amery]
  • A. Yuman
    Yuman is a Native American language family of the southwestern United States and northwestern Mexico, encompassing several related indigenous languages and peoples.
  • B. Amenia
    Amenia is a small rural town in eastern Dutchess County, New York, known for its scenic Hudson Valley landscapes and historic character.
  • C. Frances
    Frances is a feminine given name of Latin origin, commonly used in English-speaking countries.
  • D. Malia
    Malia is the elder daughter of former U.S. President Barack Obama and former First Lady Michelle Obama.
  • E. Zuidland
    Zuidland is a village in the western Netherlands, located in the province of South Holland.
  • 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: Amery
Triple: [Julian Amery, familyName, Amery]
Generated description
Amery is an English surname most notably associated with a British political family, including Conservative politician Julian Amery.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Amery
Target entity description: Amery is an English surname most notably associated with a British political family, including Conservative politician Julian Amery.
  • A. Yuman
    Yuman is a Native American language family of the southwestern United States and northwestern Mexico, encompassing several related indigenous languages and peoples.
  • B. Amenia
    Amenia is a small rural town in eastern Dutchess County, New York, known for its scenic Hudson Valley landscapes and historic character.
  • C. Frances
    Frances is a feminine given name of Latin origin, commonly used in English-speaking countries.
  • D. Malia
    Malia is the elder daughter of former U.S. President Barack Obama and former First Lady Michelle Obama.
  • E. Zuidland
    Zuidland is a village in the western Netherlands, located in the province of South Holland.
  • 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_69a49379d09c8190ac7e00b24e2810b1 completed March 1, 2026, 7:28 p.m.
NER Named-entity recognition batch_69a49b9d1e68819096a9b5e7b2e83d6e completed March 1, 2026, 8:03 p.m.
NED1 Entity disambiguation (via context triple) batch_69a5216c43148190961ff8cea8305b7e completed March 2, 2026, 5:34 a.m.
NEDg Description generation batch_69a5220225c881909a85dd8496954ba9 completed March 2, 2026, 5:37 a.m.
NED2 Entity disambiguation (via description) batch_69a522a84cf481908eeb3b6d7c2cb0d7 completed March 2, 2026, 5:39 a.m.
Created at: March 1, 2026, 7:33 p.m.