Triple

T9199907
Position Surface form Disambiguated ID Type / Status
Subject Middle Guinea E220809 entity
Predicate hasMajorCity P316 FINISHED
Object Tougué
Tougué is a town and administrative center in northern Guinea, located in the Middle Guinea region.
E784219 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: Tougué | Statement: [Middle Guinea, hasMajorCity, Tougué]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Tougué
Context triple: [Middle Guinea, hasMajorCity, Tougué]
  • A. Houegbadja
    Houegbadja was an early king of the Kingdom of Dahomey in present-day Benin, credited with consolidating the state’s power and laying the foundations for its royal institutions.
  • B. Chàhn
    Chàhn is the Yale romanization of the common Cantonese surname 陳, often rendered as "Chan" in English.
  • C. King Ghezo
    King Ghezo was a 19th-century ruler of the West African Kingdom of Dahomey known for military expansion, administrative reforms, and his complex role in the Atlantic slave trade.
  • D. Khshayarsha
    Khshayarsha is the Old Persian name for Xerxes I, the powerful Achaemenid king who ruled the Persian Empire in the early 5th century BCE and led the invasion of Greece.
  • E. Esen Taishi
    Esen Taishi was a powerful 15th-century Oirat Mongol leader who briefly unified much of Mongolia and Central Asia and even captured the Ming emperor Zhengtong in 1449.
  • 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: Tougué
Triple: [Middle Guinea, hasMajorCity, Tougué]
Generated description
Tougué is a town and administrative center in northern Guinea, located in the Middle Guinea region.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Tougué
Target entity description: Tougué is a town and administrative center in northern Guinea, located in the Middle Guinea region.
  • A. Houegbadja
    Houegbadja was an early king of the Kingdom of Dahomey in present-day Benin, credited with consolidating the state’s power and laying the foundations for its royal institutions.
  • B. Chàhn
    Chàhn is the Yale romanization of the common Cantonese surname 陳, often rendered as "Chan" in English.
  • C. King Ghezo
    King Ghezo was a 19th-century ruler of the West African Kingdom of Dahomey known for military expansion, administrative reforms, and his complex role in the Atlantic slave trade.
  • D. Khshayarsha
    Khshayarsha is the Old Persian name for Xerxes I, the powerful Achaemenid king who ruled the Persian Empire in the early 5th century BCE and led the invasion of Greece.
  • E. Esen Taishi
    Esen Taishi was a powerful 15th-century Oirat Mongol leader who briefly unified much of Mongolia and Central Asia and even captured the Ming emperor Zhengtong in 1449.
  • 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_69ca83e8e9248190862cf3e41693b310 completed March 30, 2026, 2:08 p.m.
NER Named-entity recognition batch_69ccd881c5d48190bbc33fac71a1d849 completed April 1, 2026, 8:34 a.m.
NED1 Entity disambiguation (via context triple) batch_69d05c451210819091188151d799e4cb completed April 4, 2026, 12:33 a.m.
NEDg Description generation batch_69d05dbbe0d08190a15107c17948167f completed April 4, 2026, 12:39 a.m.
NED2 Entity disambiguation (via description) batch_69d05e34ae6881908172770c6097a5e5 completed April 4, 2026, 12:41 a.m.
Created at: March 30, 2026, 7:25 p.m.