Triple

T19672416
Position Surface form Disambiguated ID Type / Status
Subject University of Dodoma E472364 entity
Predicate abbreviation P43 FINISHED
Object UDOM
UDOM is a public university in Dodoma, Tanzania, known for its wide range of academic programs and role in expanding higher education in the country.
 E1389193 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: UDOM | Statement: [University of Dodoma, abbreviation, UDOM]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: UDOM
Context triple: [University of Dodoma, abbreviation, UDOM]
  • A. UUMO
    UUMO is the ICAO airport code assigned to Ostafyevo International Airport near Moscow, Russia.
  • B. UDM
    UDM (Unified Data Management) is a 5G core network function responsible for managing subscriber data, authentication credentials, and subscription profiles across the mobile network.
  • C. UMA
    UMA is the acronym for the Arab Maghreb Union, a regional organization aimed at promoting economic and political cooperation among North African countries.
  • D. UMA
    UMA is a regional public university in Augusta, Maine, offering a range of undergraduate and professional programs with a focus on accessibility and nontraditional students.
  • E. UMA
    UMA is the abbreviated name for the Unidad de Medios Aéreos, a specialized aerial media or air support unit typically involved in surveillance, transport, and operational support missions.
  • 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: UDOM
Triple: [University of Dodoma, abbreviation, UDOM]
Generated description
UDOM is a public university in Dodoma, Tanzania, known for its wide range of academic programs and role in expanding higher education in the country.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: UDOM
Target entity description: UDOM is a public university in Dodoma, Tanzania, known for its wide range of academic programs and role in expanding higher education in the country.
  • A. UUMO
    UUMO is the ICAO airport code assigned to Ostafyevo International Airport near Moscow, Russia.
  • B. UDM
    UDM (Unified Data Management) is a 5G core network function responsible for managing subscriber data, authentication credentials, and subscription profiles across the mobile network.
  • C. UMA
    UMA is the abbreviated name for the Unidad de Medios Aéreos, a specialized aerial media or air support unit typically involved in surveillance, transport, and operational support missions.
  • D. UMA
    UMA is the acronym for the Arab Maghreb Union, a regional organization aimed at promoting economic and political cooperation among North African countries.
  • E. UMA
    UMA is a regional public university in Augusta, Maine, offering a range of undergraduate and professional programs with a focus on accessibility and nontraditional students.
  • 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_69d8e514f2e08190ba70a4449519d218 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e6416d61008190af531c6d346d7da1 completed April 20, 2026, 3:08 p.m.
NED1 Entity disambiguation (via context triple) batch_6a0787c08af48190a7253a74bca96aa6 completed May 15, 2026, 8:53 p.m.
NEDg Description generation batch_6a07889ccc9c8190be812f5c9eb0bfe7 completed May 15, 2026, 8:57 p.m.
NED2 Entity disambiguation (via description) batch_6a078a1b11ec81908671f431c39b9496 completed May 15, 2026, 9:03 p.m.
Created at: April 10, 2026, 1:45 p.m.