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.