Triple

T26605884
Position Surface form Disambiguated ID Type / Status
Subject Tanzania Airports Authority E667768 entity
Predicate operatesAirport P38515 FINISHED
Object Pemba Airport
Pemba Airport is a regional airport serving Pemba Island in Tanzania, providing domestic connections and access to the Zanzibar Archipelago.
E1762902 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: Pemba Airport | Statement: [Tanzania Airports Authority, operatesAirport, Pemba Airport]
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: Pemba Airport
Triple: [Tanzania Airports Authority, operatesAirport, Pemba Airport]
Generated description
Pemba Airport is a regional airport serving Pemba Island in Tanzania, providing domestic connections and access to the Zanzibar Archipelago.

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_69ee9cfd20348190bb1255d2603efb7a completed April 26, 2026, 11:17 p.m.
NER Named-entity recognition batch_69f615734f888190b144b23c68324b7e completed May 2, 2026, 3:17 p.m.
NED1 Entity disambiguation (via context triple) batch_6a126247cd448190aca7e73caceda298 completed May 24, 2026, 2:28 a.m.
NEDg Description generation batch_6a1266920d008190b029acd1c8efc214 completed May 24, 2026, 2:46 a.m.
NED2 Entity disambiguation (via description) batch_6a1266f0b7448190a158f776016efacd completed May 24, 2026, 2:48 a.m.
Created at: April 27, 2026, 2:14 a.m.