Triple

T11014362
Position Surface form Disambiguated ID Type / Status
Subject Arusha–Namanga road E260325 entity
Predicate connects P390 FINISHED
Object Namanga E381715 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: Namanga | Statement: [Arusha–Namanga road, connects, Namanga]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Namanga
Context triple: [Arusha–Namanga road, connects, Namanga]
  • A. Namanga chosen
    Namanga is a small border town between Kenya and Tanzania that serves as a key gateway for tourists traveling to Amboseli National Park.
  • B. Namutoni
    Namutoni is a historic former German fort turned tourist rest camp and lodge located on the eastern side of Etosha National Park in Namibia.
  • C. Monguno
    Monguno is a town and local government area in Borno State, northeastern Nigeria, known for its strategic location and role in regional security dynamics.
  • D. Nabulungi
    Nabulungi is a central character in the musical "The Book of Mormon," a hopeful and idealistic young Ugandan woman who becomes a key follower of the missionaries’ teachings.
  • E. Rakai Kayuwangi
    Rakai Kayuwangi was a ruler of the Mataram Kingdom in Central Java, known from Old Javanese inscriptions as one of the early monarchs in the Medang (Mataram) dynasty.
  • 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_69d6aa9687448190b28d353b1b6a610e completed April 8, 2026, 7:20 p.m.
NER Named-entity recognition batch_69d797a49f648190a5144625d09dec6f completed April 9, 2026, 12:12 p.m.
NED1 Entity disambiguation (via context triple) batch_69e3a98725808190903639866a3e745f completed April 18, 2026, 3:55 p.m.
Created at: April 8, 2026, 9:25 p.m.