Triple

T17718705
Position Surface form Disambiguated ID Type / Status
Subject Mbabane E442273 entity
Predicate locatedIn P40 FINISHED
Object Hhohho Region NE NERFINISHED

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: Hhohho Region | Statement: [Mbabane, locatedIn, Hhohho Region]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Hhohho Region
Context triple: [Mbabane, locatedIn, Hhohho Region]
  • A. Hhohho Region chosen
    Hhohho Region is an administrative region in northern Eswatini that includes the national capital, Mbabane, and is known for its mountainous terrain.
  • B. Ménaka Region
    Ménaka Region is an administrative region in eastern Mali, known for its predominantly Tuareg and other pastoralist communities and its location in the Sahel near the Niger border.
  • C. Tamba region
    The Tamba region is a historical and rural area in central Japan, known for its mountainous landscapes, traditional agriculture, and preserved old towns.
  • D. Faranah Region
    Faranah Region is an administrative region in central Guinea known for its agricultural activities and location along the upper Niger River.
  • E. Dikhil Region
    Dikhil Region is an administrative region in southwestern Djibouti known for its arid landscapes, border location near Ethiopia, and the town of Dikhil as its capital.
  • F. None of above.
  • G. Unsure - the case is ambiguous/there is not enough information to decide.

Provenance (2 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_69d8b9ec79688190b86bdcef85a7b3aa completed April 10, 2026, 8:50 a.m.
NER Named-entity recognition batch_69e474834aec81909ab7e8224c5a39d7 completed April 19, 2026, 6:21 a.m.
Created at: April 10, 2026, 10:06 a.m.