Triple

T6962012
Position Surface form Disambiguated ID Type / Status
Subject Adobe Fonts E161389 entity
Predicate includesFoundry P73805 FINISHED
Object Type Network
Type Network is a collaborative type foundry and distribution platform that offers a curated collection of high-quality digital fonts from independent designers and foundries.
E630489 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: Type Network | Statement: [Adobe Fonts, includesFoundry, Type Network]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Type Network
Context triple: [Adobe Fonts, includesFoundry, Type Network]
  • A. Network
    Network is a 1976 satirical drama film directed by Sidney Lumet that critiques television news and media sensationalism.
  • B. Networker
    Networker is a family of electric and diesel multiple-unit trains used on suburban and regional rail services in southeast England.
  • C. NET
    NET is the stock ticker symbol for Cloudflare, Inc., a company that provides cloud-based web infrastructure and security services.
  • D. NET
    NET was a U.S. public television network that served as the primary national distributor of educational and cultural programming before being succeeded by PBS.
  • E. NET
    NET is the NCAA’s primary ranking system used to evaluate and seed college basketball teams for postseason tournaments.
  • 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: Type Network
Triple: [Adobe Fonts, includesFoundry, Type Network]
Generated description
Type Network is a collaborative type foundry and distribution platform that offers a curated collection of high-quality digital fonts from independent designers and foundries.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Type Network
Target entity description: Type Network is a collaborative type foundry and distribution platform that offers a curated collection of high-quality digital fonts from independent designers and foundries.
  • A. Network
    Network is a 1976 satirical drama film directed by Sidney Lumet that critiques television news and media sensationalism.
  • B. Networker
    Networker is a family of electric and diesel multiple-unit trains used on suburban and regional rail services in southeast England.
  • C. NET
    NET is the stock ticker symbol for Cloudflare, Inc., a company that provides cloud-based web infrastructure and security services.
  • D. NET
    NET was a U.S. public television network that served as the primary national distributor of educational and cultural programming before being succeeded by PBS.
  • E. NET
    NET is the NCAA’s primary ranking system used to evaluate and seed college basketball teams for postseason tournaments.
  • 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_69c68853cff881908439d488924a8283 completed March 27, 2026, 1:38 p.m.
NER Named-entity recognition batch_69c6e1d144648190b7e6558246b013e3 completed March 27, 2026, 8 p.m.
NED1 Entity disambiguation (via context triple) batch_69c7589c587c8190b97523b5ac2ab958 completed March 28, 2026, 4:27 a.m.
NEDg Description generation batch_69c759553fe081909881c8d2ae680dfe completed March 28, 2026, 4:30 a.m.
NED2 Entity disambiguation (via description) batch_69c759c79de48190bd3e079c07a9158a completed March 28, 2026, 4:32 a.m.
Created at: March 27, 2026, 2:30 p.m.