Triple

T19835907
Position Surface form Disambiguated ID Type / Status
Subject Kenya Navy E476593 entity
Predicate hasBase P2909 FINISHED
Object Kilindini
Kilindini is a deep-water harbor area in Mombasa, Kenya, that serves as a key naval and commercial port on the Indian Ocean.
 E1396640 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: Kilindini | Statement: [Kenya Navy, hasBase, Kilindini]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Kilindini
Context triple: [Kenya Navy, hasBase, Kilindini]
  • A. Kilana
    Kilana is a Vorta official serving the Dominion who appears in Star Trek: Deep Space Nine as a cunning and diplomatic antagonist.
  • B. Kile
    Kile is a KDE-based integrated LaTeX editor that provides tools for writing, compiling, and previewing LaTeX documents efficiently.
  • C. Kuiil
    Kuiil is a wise and skilled Ugnaught moisture farmer and former Imperial indentured servant who aids the Mandalorian with his technical expertise and calm counsel in the Star Wars series "The Mandalorian."
  • D. Kilivila
    Kilivila is an Austronesian language spoken by the Trobriand Islanders of Papua New Guinea.
  • E. Kiume
    Kiume is one of the main human performers in Disney's "Festival of the Lion King" stage show, leading songs and interacting with the audience as part of the production.
  • 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: Kilindini
Triple: [Kenya Navy, hasBase, Kilindini]
Generated description
Kilindini is a deep-water harbor area in Mombasa, Kenya, that serves as a key naval and commercial port on the Indian Ocean.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Kilindini
Target entity description: Kilindini is a deep-water harbor area in Mombasa, Kenya, that serves as a key naval and commercial port on the Indian Ocean.
  • A. Kilana
    Kilana is a Vorta official serving the Dominion who appears in Star Trek: Deep Space Nine as a cunning and diplomatic antagonist.
  • B. Kile
    Kile is a KDE-based integrated LaTeX editor that provides tools for writing, compiling, and previewing LaTeX documents efficiently.
  • C. Kuiil
    Kuiil is a wise and skilled Ugnaught moisture farmer and former Imperial indentured servant who aids the Mandalorian with his technical expertise and calm counsel in the Star Wars series "The Mandalorian."
  • D. Kilivila
    Kilivila is an Austronesian language spoken by the Trobriand Islanders of Papua New Guinea.
  • E. Kiume
    Kiume is one of the main human performers in Disney's "Festival of the Lion King" stage show, leading songs and interacting with the audience as part of the production.
  • 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_69d8e51c7c188190b926f3a2a7b5f881 completed April 10, 2026, 11:55 a.m.
NER Named-entity recognition batch_69e656d275608190841b23de167c401e completed April 20, 2026, 4:39 p.m.
NED1 Entity disambiguation (via context triple) batch_6a07ccdc05848190a353aa1d51108555 completed May 16, 2026, 1:48 a.m.
NEDg Description generation batch_6a07ce38b6508190aa43a893b01c4d80 completed May 16, 2026, 1:54 a.m.
NED2 Entity disambiguation (via description) batch_6a07ceea12e881908a88a34c40047ecc completed May 16, 2026, 1:56 a.m.
Created at: April 10, 2026, 1:50 p.m.