Triple

T3904887
Position Surface form Disambiguated ID Type / Status
Subject Swazi people E90581 entity
Predicate capitalCityAssociated P8146 FINISHED
Object Mbabane E95282 NE FINISHED

How this triple was built (2 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: Mbabane | Statement: [Swazi people, capitalCityAssociated, Mbabane]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Mbabane
Context triple: [Swazi people, capitalCityAssociated, Mbabane]
  • A. Mbabane chosen
    Mbabane is the largest city and administrative center of Eswatini, located in the country's western highlands.
  • B. Manzini
    Manzini is a major city in Eswatini that serves as an important commercial and transport hub of the country.
  • C. Masandawana
    Masandawana is the popular nickname of South African football club Mamelodi Sundowns F.C., one of the country’s most successful and widely supported teams.
  • D. Makhuwa
    Makhuwa is a major Bantu language spoken primarily in northern Mozambique by the Makhuwa people.
  • E. Mzuzu
    Mzuzu is a major city in northern Malawi known as an important commercial and administrative center for the region.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (3 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_69aed95d315881908cbf1bf4a7215fbf completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aeed0fb9888190add847806555a14a completed March 9, 2026, 3:53 p.m.
NED1 Entity disambiguation (via context triple) batch_69b528540ad48190ac86774c76a2ffd4 completed March 14, 2026, 9:20 a.m.
Created at: March 9, 2026, 3:22 p.m.