Triple

T1940944
Position Surface form Disambiguated ID Type / Status
Subject Frank Howard E41551 entity
Predicate familyName P18 FINISHED
Object Howard
Howard is a common English surname of Old English origin, borne by numerous notable figures across politics, sports, and the arts.
 E118997 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: Howard | Statement: [Frank Howard, familyName, Howard]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Howard
Context triple: [Frank Howard, familyName, Howard]
  • A. Howard
    Howard is the middle name of William Howard Taft, the 27th president of the United States and later Chief Justice of the Supreme Court.
  • B. Howard
    Howard is the middle name of Edwin H. Armstrong, the pioneering American electrical engineer and inventor of FM radio.
  • C. Howard
    Howard is a volume series of early U.S. Supreme Court case reports compiled by Benjamin Chew Howard, later incorporated into the official United States Reports.
  • D. Howard
    Howard is a major Chicago Transit Authority rail station that serves as a key northern terminal and transfer point for multiple 'L' lines.
  • E. Howard
    Howard is the given name of the influential American film director, producer, and screenwriter Howard Hawks.
  • 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: Howard
Triple: [Frank Howard, familyName, Howard]
Generated description
Howard is a common English surname of Old English origin, borne by numerous notable figures across politics, sports, and the arts.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Howard
Target entity description: Howard is a common English surname of Old English origin, borne by numerous notable figures across politics, sports, and the arts.
  • A. Howard chosen
    Howard is a common English surname shared by numerous notable figures across entertainment, politics, and other fields.
  • B. Howard
    Howard is the given name of the influential American film director, producer, and screenwriter Howard Hawks.
  • C. Howard
    Howard is the middle name of William Howard Taft, the 27th president of the United States and later Chief Justice of the Supreme Court.
  • D. Howard
    Howard is the given first name of Ward Cunningham, the American computer programmer best known for creating the first wiki.
  • E. Howard
    Howard is the middle name of Edwin H. Armstrong, the pioneering American electrical engineer and inventor of FM radio.
  • F. None of above.

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_69a88649b24c819080047f26b6db2ded completed March 4, 2026, 7:21 p.m.
NER Named-entity recognition batch_69abb2fb21fc8190929ea4a87ef4402e completed March 7, 2026, 5:09 a.m.
NED1 Entity disambiguation (via context triple) batch_69ae5d81d0908190b2e1780a79a3def8 completed March 9, 2026, 5:41 a.m.
NEDg Description generation batch_69ae5e027ea48190a052556d43c39f73 completed March 9, 2026, 5:43 a.m.
NED2 Entity disambiguation (via description) batch_69ae5ea4edcc81908829e4bd64ce0aea completed March 9, 2026, 5:46 a.m.
Created at: March 4, 2026, 7:36 p.m.