Triple

T10924595
Position Surface form Disambiguated ID Type / Status
Subject Kenya Revenue Authority E258033 entity
Predicate shortName P43 FINISHED
Object KRA
KRA is Kenya’s national tax collection and revenue administration agency responsible for assessing, collecting, and accounting for government revenue.
 E894066 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: KRA | Statement: [Kenya Revenue Authority, shortName, KRA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: KRA
Context triple: [Kenya Revenue Authority, shortName, KRA]
  • A. KRCA
    KRCA is a Los Angeles-area television station that currently operates as a Spanish-language independent outlet serving Southern California viewers.
  • B. KRU
    KRU is a German vehicle registration code assigned to the district of Günzburg in the state of Bavaria.
  • C. Kra 1
    Kra 1 is the designated type strain of the hyperthermophilic archaeon Thermoproteus tenax, used as the reference for defining the species’ characteristics.
  • D. RKA
    RKA is the Russian Space Agency that managed Russia’s human spaceflight activities, including operations of the Mir space station.
  • E. KRAL
    KRAL is the ICAO airport code for Riverside Municipal Airport in Riverside, California, United States.
  • 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: KRA
Triple: [Kenya Revenue Authority, shortName, KRA]
Generated description
KRA is Kenya’s national tax collection and revenue administration agency responsible for assessing, collecting, and accounting for government revenue.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: KRA
Target entity description: KRA is Kenya’s national tax collection and revenue administration agency responsible for assessing, collecting, and accounting for government revenue.
  • A. KRCA
    KRCA is a Los Angeles-area television station that currently operates as a Spanish-language independent outlet serving Southern California viewers.
  • B. KRU
    KRU is a German vehicle registration code assigned to the district of Günzburg in the state of Bavaria.
  • C. Kra 1
    Kra 1 is the designated type strain of the hyperthermophilic archaeon Thermoproteus tenax, used as the reference for defining the species’ characteristics.
  • D. RKA
    RKA is the Russian Space Agency that managed Russia’s human spaceflight activities, including operations of the Mir space station.
  • E. KRAL
    KRAL is the ICAO airport code for Riverside Municipal Airport in Riverside, California, United States.
  • 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_69d6aa864ed88190818280ab6791d065 completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d7708f7ab48190b60a4bb8fdb17c8e completed April 9, 2026, 9:25 a.m.
NED1 Entity disambiguation (via context triple) batch_69e217369b648190914c58db6f6e0200 completed April 17, 2026, 11:19 a.m.
NEDg Description generation batch_69e21d8a2e6881909b33cbe4ab919315 completed April 17, 2026, 11:46 a.m.
NED2 Entity disambiguation (via description) batch_69e21eaa1e9881909f3b276e0ff0c511 completed April 17, 2026, 11:51 a.m.
Created at: April 8, 2026, 9:22 p.m.