Triple

T4819098
Position Surface form Disambiguated ID Type / Status
Subject Alfred B. Mullett E107664 entity
Predicate familyName P18 FINISHED
Object Mullett
Mullett is a surname most notably associated with Alfred B. Mullett, a 19th-century American architect known for designing prominent federal buildings.
 E471894 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: Mullett | Statement: [Alfred B. Mullett, familyName, Mullett]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Mullett
Context triple: [Alfred B. Mullett, familyName, Mullett]
  • A. Ramolino
    Ramolino is an Italian surname historically associated with Corsican nobility and notably borne by Letizia Ramolino, the mother of Napoleon Bonaparte.
  • B. Keefer
    Keefer was a distinguished racing greyhound renowned for its achievements on the track, earning induction into the Greyhound Hall of Fame.
  • C. Hunte
    The Hunte is a river in northwestern Germany that flows through Lower Saxony before joining the Weser.
  • D. Milhous
    Milhous is the distinctive middle name of Richard Nixon, the 37th president of the United States.
  • E. Mulkey
    Mulkey is the surname of Kim Mulkey, a prominent American women's college basketball coach and former player.
  • 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: Mullett
Triple: [Alfred B. Mullett, familyName, Mullett]
Generated description
Mullett is a surname most notably associated with Alfred B. Mullett, a 19th-century American architect known for designing prominent federal buildings.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Mullett
Target entity description: Mullett is a surname most notably associated with Alfred B. Mullett, a 19th-century American architect known for designing prominent federal buildings.
  • A. Ramolino
    Ramolino is an Italian surname historically associated with Corsican nobility and notably borne by Letizia Ramolino, the mother of Napoleon Bonaparte.
  • B. Keefer
    Keefer was a distinguished racing greyhound renowned for its achievements on the track, earning induction into the Greyhound Hall of Fame.
  • C. Hunte
    The Hunte is a river in northwestern Germany that flows through Lower Saxony before joining the Weser.
  • D. Milhous
    Milhous is the distinctive middle name of Richard Nixon, the 37th president of the United States.
  • E. Mulkey
    Mulkey is the surname of Kim Mulkey, a prominent American women's college basketball coach and former player.
  • 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_69bd43f9efa081908314cb3e94fa1695 completed March 20, 2026, 12:56 p.m.
NER Named-entity recognition batch_69bd6c96f4dc81909e3186159b5c75ab completed March 20, 2026, 3:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69be4dbbfe588190bae0aca210bea2bc completed March 21, 2026, 7:50 a.m.
NEDg Description generation batch_69be4f6ceb60819080dc1ee93950a7f0 completed March 21, 2026, 7:57 a.m.
NED2 Entity disambiguation (via description) batch_69be4fbc83188190af2c9767aa9272a7 completed March 21, 2026, 7:58 a.m.
Created at: March 20, 2026, 1:24 p.m.