Triple

T10247141
Position Surface form Disambiguated ID Type / Status
Subject Estuaire Province E240244 entity
Predicate contains P35 FINISHED
Object Kango
Kango is a town in western Gabon known as a transport hub along the N1 road and a gateway between the capital Libreville and the interior regions.
E853671 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: Kango | Statement: [Estuaire Province, contains, Kango]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kango
Context triple: [Estuaire Province, contains, Kango]
  • A. Kangha
    Kangha is a small wooden comb that serves as one of the Five Ks in Sikhism, symbolizing cleanliness and discipline for initiated Sikhs.
  • B. Kangar
    Kangar is the main administrative and commercial center of the Malaysian state of Perlis.
  • C. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of Papua New Guinea.
  • D. Kwayo
    Kwayo is an alternative name for the Kwaio language, an Austronesian language spoken by the Kwaio people of Malaita in the Solomon Islands.
  • E. Kwangde
    Kwangde is a prominent Himalayan mountain massif in Nepal’s Khumbu region, known for its steep faces and challenging climbing routes.
  • 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: Kango
Triple: [Estuaire Province, contains, Kango]
Generated description
Kango is a town in western Gabon known as a transport hub along the N1 road and a gateway between the capital Libreville and the interior regions.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kango
Target entity description: Kango is a town in western Gabon known as a transport hub along the N1 road and a gateway between the capital Libreville and the interior regions.
  • A. Kangha
    Kangha is a small wooden comb that serves as one of the Five Ks in Sikhism, symbolizing cleanliness and discipline for initiated Sikhs.
  • B. Kangar
    Kangar is the main administrative and commercial center of the Malaysian state of Perlis.
  • C. Kandas
    Kandas is an Oceanic language of the Meso-Melanesian subgroup spoken in parts of Papua New Guinea.
  • D. Kwayo
    Kwayo is an alternative name for the Kwaio language, an Austronesian language spoken by the Kwaio people of Malaita in the Solomon Islands.
  • E. Kwangde
    Kwangde is a prominent Himalayan mountain massif in Nepal’s Khumbu region, known for its steep faces and challenging climbing routes.
  • 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_69d381a7e198819090280d5ab885d59e completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d22e0d4c8190a6712859924e9d3d completed April 7, 2026, 9:45 a.m.
NED1 Entity disambiguation (via context triple) batch_69d6f7ade8448190830d950b7cee0c34 completed April 9, 2026, 12:49 a.m.
NEDg Description generation batch_69d6fa303d4c8190b9f1c3addf7d8b09 completed April 9, 2026, 1 a.m.
NED2 Entity disambiguation (via description) batch_69d6ff301d488190b18f1e02bbf1dada completed April 9, 2026, 1:21 a.m.
Created at: April 6, 2026, 11:27 a.m.