Triple

T3793116
Position Surface form Disambiguated ID Type / Status
Subject Cabinda E89703 entity
Predicate hasCity P316 FINISHED
Object Landana
Landana is a coastal town in Angola’s Cabinda exclave, historically known as a regional trading and missionary center.
 E390882 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: Landana | Statement: [Cabinda, hasCity, Landana]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: Landana
Context triple: [Cabinda, hasCity, Landana]
  • A. Palaonda
    Palaonda is an indoor ice arena in Bolzano, Italy, primarily used for ice hockey and other sporting and entertainment events.
  • B. Malax
    Malax is a small coastal municipality in western Finland known for its Swedish-speaking majority and rural Ostrobothnian landscapes.
  • C. Balmaha
    Balmaha is a small Scottish village on the eastern shore of Loch Lomond, known as a gateway to the loch’s islands and a popular stop on the West Highland Way walking route.
  • D. Ronga
    Ronga is a Bantu language spoken primarily in southern Mozambique, known for contributing vocabulary and structural features to African varieties of Portuguese.
  • E. Gilga
    Gilga is a production company known for its work on the television series "Swarm."
  • 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: Landana
Triple: [Cabinda, hasCity, Landana]
Generated description
Landana is a coastal town in Angola’s Cabinda exclave, historically known as a regional trading and missionary center.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: Landana
Target entity description: Landana is a coastal town in Angola’s Cabinda exclave, historically known as a regional trading and missionary center.
  • A. Palaonda
    Palaonda is an indoor ice arena in Bolzano, Italy, primarily used for ice hockey and other sporting and entertainment events.
  • B. Malax
    Malax is a small coastal municipality in western Finland known for its Swedish-speaking majority and rural Ostrobothnian landscapes.
  • C. Balmaha
    Balmaha is a small Scottish village on the eastern shore of Loch Lomond, known as a gateway to the loch’s islands and a popular stop on the West Highland Way walking route.
  • D. Ronga
    Ronga is a Bantu language spoken primarily in southern Mozambique, known for contributing vocabulary and structural features to African varieties of Portuguese.
  • E. Gilga
    Gilga is a production company known for its work on the television series "Swarm."
  • 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_69aed9597d6881909b6ee3b9de859223 completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aee76b809c81908312f308fbe85bf4 completed March 9, 2026, 3:29 p.m.
NED1 Entity disambiguation (via context triple) batch_69b4fb1f7a20819082d2ff104167d98b completed March 14, 2026, 6:07 a.m.
NEDg Description generation batch_69b4fc6683848190a332fcb37df77934 completed March 14, 2026, 6:12 a.m.
NED2 Entity disambiguation (via description) batch_69b4fcc395ec8190a781e982b935c2f6 completed March 14, 2026, 6:14 a.m.
Created at: March 9, 2026, 3:15 p.m.