Triple

T14137751
Position Surface form Disambiguated ID Type / Status
Subject Susan Kare E350341 entity
Predicate familyName P18 FINISHED
Object Kare
Kare is the surname of Susan Kare, a pioneering graphic designer best known for creating many of the original interface icons and typefaces for the Apple Macintosh.
 E316198 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: Kare | Statement: [Susan Kare, familyName, Kare]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kare
Context triple: [Susan Kare, familyName, Kare]
  • A. Kare
    Kare is an alternate name for the Cari language, an indigenous language of the Cariban family spoken in parts of South America.
  • B. Karait
    Karait is a small but deadly brown snake in Rudyard Kipling’s “Rikki-Tikki-Tavi,” known as one of the venomous antagonists threatening the human family.
  • C. Kaei
    Kaei was a Japanese era name (nengō) of the late Edo period, notable for encompassing events such as the arrival of Commodore Perry and the opening of Japan to the West.
  • D. Kaei
    Kaei is an alternate name for the Kayeli language, an Austronesian language historically spoken on Buru Island in Indonesia.
  • E. Kasari
    Kasari is a town located on Amami Ōshima in Japan’s Kagoshima Prefecture, known for its subtropical island scenery and coastal environment.
  • 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: Kare
Triple: [Susan Kare, familyName, Kare]
Generated description
Kare is the surname of Susan Kare, a pioneering graphic designer best known for creating many of the original interface icons and typefaces for the Apple Macintosh.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kare
Target entity description: Kare is the surname of Susan Kare, a pioneering graphic designer best known for creating many of the original interface icons and typefaces for the Apple Macintosh.
  • A. Kare chosen
    Kare is an alternate name for the Cari language, an indigenous language of the Cariban family spoken in parts of South America.
  • B. Karait
    Karait is a small but deadly brown snake in Rudyard Kipling’s “Rikki-Tikki-Tavi,” known as one of the venomous antagonists threatening the human family.
  • C. Kaei
    Kaei was a Japanese era name (nengō) of the late Edo period, notable for encompassing events such as the arrival of Commodore Perry and the opening of Japan to the West.
  • D. Kaei
    Kaei is an alternate name for the Kayeli language, an Austronesian language historically spoken on Buru Island in Indonesia.
  • E. Kasari
    Kasari is a town located on Amami Ōshima in Japan’s Kagoshima Prefecture, known for its subtropical island scenery and coastal environment.
  • 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_69d827865f608190b311820428ae027b completed April 9, 2026, 10:26 p.m.
NER Named-entity recognition batch_69de610fb86c81909eb26bf9c13696ca completed April 14, 2026, 3:45 p.m.
NED1 Entity disambiguation (via context triple) batch_69fcdf16079c819080a74cd8a6eb37a6 completed May 7, 2026, 6:51 p.m.
NEDg Description generation batch_69fce89cf5b08190a2a610f49a4b6f90 completed May 7, 2026, 7:31 p.m.
NED2 Entity disambiguation (via description) batch_69fce984be2881909b38e3d9e4fac243 completed May 7, 2026, 7:35 p.m.
Created at: April 10, 2026, 12:38 a.m.