Triple

T8327777
Position Surface form Disambiguated ID Type / Status
Subject Lofa County E194997 entity
Predicate hasCity P316 FINISHED
Object Kolahun
Kolahun is a town in northwestern Liberia that serves as one of the main local centers of administration and commerce in Lofa County.
E725268 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: Kolahun | Statement: [Lofa County, hasCity, Kolahun]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: Kolahun
Context triple: [Lofa County, hasCity, Kolahun]
  • A. Kolakham
    Kolakham is a small, scenic village in the Kalimpong district of West Bengal, India, known for its tranquil forests, mountain views, and proximity to Neora Valley National Park.
  • B. Kulon
    Kulon is an extinct Papuan language once spoken in the interior of West Papua, Indonesia.
  • C. Kololo
    Kololo refers to the Sotho-speaking people whose 19th-century migration and conquest in south-central Africa significantly influenced the formation and language of the Lozi kingdom in present-day Zambia.
  • D. Kolane
    Kolane is a small municipality located within Zadar County in Croatia.
  • E. Kahola
    Kahola is an ancient Vedic sage mentioned in Hindu scriptures, notably as a participant in philosophical dialogues in the Upanishads.
  • 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: Kolahun
Triple: [Lofa County, hasCity, Kolahun]
Generated description
Kolahun is a town in northwestern Liberia that serves as one of the main local centers of administration and commerce in Lofa County.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: Kolahun
Target entity description: Kolahun is a town in northwestern Liberia that serves as one of the main local centers of administration and commerce in Lofa County.
  • A. Kolakham
    Kolakham is a small, scenic village in the Kalimpong district of West Bengal, India, known for its tranquil forests, mountain views, and proximity to Neora Valley National Park.
  • B. Kulon
    Kulon is an extinct Papuan language once spoken in the interior of West Papua, Indonesia.
  • C. Kololo
    Kololo refers to the Sotho-speaking people whose 19th-century migration and conquest in south-central Africa significantly influenced the formation and language of the Lozi kingdom in present-day Zambia.
  • D. Kolane
    Kolane is a small municipality located within Zadar County in Croatia.
  • E. Kahola
    Kahola is an ancient Vedic sage mentioned in Hindu scriptures, notably as a participant in philosophical dialogues in the Upanishads.
  • 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_69ca82e87f2c8190bdb71ee29dfc642d completed March 30, 2026, 2:04 p.m.
NER Named-entity recognition batch_69cb7f8243288190b1ae74d69395fc91 completed March 31, 2026, 8:02 a.m.
NED1 Entity disambiguation (via context triple) batch_69cd95b92708819097795498f9ebcdfc completed April 1, 2026, 10:01 p.m.
NEDg Description generation batch_69cdab60ec308190a9001f9235e556b4 completed April 1, 2026, 11:33 p.m.
NED2 Entity disambiguation (via description) batch_69cdb2e3457c8190a2d0cb6eeb81c9ef completed April 2, 2026, 12:05 a.m.
Created at: March 30, 2026, 5:56 p.m.