Triple

T52611
Position Surface form Disambiguated ID Type / Status
Subject Interface Message Processor E1033 entity
Predicate alsoKnownAs P39 FINISHED
Object IMP
IMP is an early packet-switching node used in the ARPANET, serving as a precursor to modern internet routers.
E4013 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: IMP | Statement: [Interface Message Processor, alsoKnownAs, IMP]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: IMP
Context triple: [Interface Message Processor, alsoKnownAs, IMP]
  • A. OM
    OM is the post-nominal abbreviation used by members of the Order of Merit, a prestigious British honor recognizing distinguished service in the armed forces, science, art, literature, or the promotion of culture.
  • B. HUP
    HUP is a major academic medical center in Philadelphia that serves as the flagship teaching hospital of the University of Pennsylvania's health system.
  • C. PR
    PR is the two-letter postal abbreviation commonly used to refer to Puerto Rico, a Caribbean island and unincorporated territory of the United States.
  • D. SF
    SF is the standard two-letter postal abbreviation used to represent the city of San Francisco, California.
  • E. NAM
    NAM is the commonly used acronym for the National Academy of Medicine, a leading U.S. nonprofit institution that provides expert advice on health, medicine, and biomedical science.
  • 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: IMP
Triple: [Interface Message Processor, alsoKnownAs, IMP]
Generated description
IMP is an early packet-switching node used in the ARPANET, serving as a precursor to modern internet routers.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: IMP
Target entity description: IMP is an early packet-switching node used in the ARPANET, serving as a precursor to modern internet routers.
  • A. OM
    OM is the post-nominal abbreviation used by members of the Order of Merit, a prestigious British honor recognizing distinguished service in the armed forces, science, art, literature, or the promotion of culture.
  • B. PT
    PT is the two-letter ISO 3166-1 alpha-2 country code that uniquely identifies Portugal in international standards and systems.
  • C. HUP
    HUP is a major academic medical center in Philadelphia that serves as the flagship teaching hospital of the University of Pennsylvania's health system.
  • D. PR
    PR is the two-letter postal abbreviation commonly used to refer to Puerto Rico, a Caribbean island and unincorporated territory of the United States.
  • E. S
    S is the distinctive middle initial of U.S. President Harry S. Truman, famously not standing for any specific name but honoring both of his grandfathers.
  • 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_69a2480baefc81909951b14058479aa2 completed Feb. 28, 2026, 1:42 a.m.
NER Named-entity recognition batch_69a24b0382b48190a7ca80ade6d2e270 completed Feb. 28, 2026, 1:55 a.m.
NED1 Entity disambiguation (via context triple) batch_69a24e67187c8190950aec5d9f8ecc60 completed Feb. 28, 2026, 2:09 a.m.
NEDg Description generation batch_69a24eff3f0881909b46502175682d99 completed Feb. 28, 2026, 2:12 a.m.
NED2 Entity disambiguation (via description) batch_69a2542d9b388190bcc4581c3b79aa51 completed Feb. 28, 2026, 2:34 a.m.
Created at: Feb. 28, 2026, 1:47 a.m.