Triple
T3117302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lake Kyoga |
E65092
|
entity |
| Predicate | nearCity |
P350
|
FINISHED |
| Object |
Lira
Lira is a major town in northern Uganda that serves as an important commercial and administrative center for the surrounding region.
|
E329618
|
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: Lira | Statement: [Lake Kyoga, nearCity, Lira]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lira Context triple: [Lake Kyoga, nearCity, Lira]
-
A.
Sakarya
Sakarya is a city in northwestern Turkey known for its strategic location near the Black Sea and its role as an important industrial and transportation hub.
-
B.
Dumlupınar
Dumlupınar is a town in western Turkey best known as the decisive battlefield where Turkish forces secured victory in the 1922 Great Offensive of the Turkish War of Independence.
-
C.
Assos
Assos was an ancient Greek city in the Troad region of Asia Minor, known as a philosophical center where figures like Aristotle once lived and taught.
-
D.
Orlu
Orlu is a prominent town and commercial hub in southeastern Nigeria that serves as an important center for trade, industry, and regional administration.
-
E.
Sassoun
Sassoun is a mountainous region in historic Western Armenia, famed in Armenian folklore as the homeland of the legendary heroes of the national epic.
- 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: Lira Triple: [Lake Kyoga, nearCity, Lira]
Generated description
Lira is a major town in northern Uganda that serves as an important commercial and administrative center for the surrounding region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lira Target entity description: Lira is a major town in northern Uganda that serves as an important commercial and administrative center for the surrounding region.
-
A.
Sakarya
Sakarya is a city in northwestern Turkey known for its strategic location near the Black Sea and its role as an important industrial and transportation hub.
-
B.
Dumlupınar
Dumlupınar is a town in western Turkey best known as the decisive battlefield where Turkish forces secured victory in the 1922 Great Offensive of the Turkish War of Independence.
-
C.
Assos
Assos was an ancient Greek city in the Troad region of Asia Minor, known as a philosophical center where figures like Aristotle once lived and taught.
-
D.
Orlu
Orlu is a prominent town and commercial hub in southeastern Nigeria that serves as an important center for trade, industry, and regional administration.
-
E.
Sassoun
Sassoun is a mountainous region in historic Western Armenia, famed in Armenian folklore as the homeland of the legendary heroes of the national epic.
- 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_69ad857fcc088190b0c4d45a5cde6f61 |
completed | March 8, 2026, 2:19 p.m. |
| NER | Named-entity recognition | batch_69ada4e73cc88190846ef37ccf1a0de7 |
completed | March 8, 2026, 4:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b20f606fc881908754a78e6aa2de64 |
completed | March 12, 2026, 12:57 a.m. |
| NEDg | Description generation | batch_69b2134b5eac8190adadc4a27cfe10c7 |
completed | March 12, 2026, 1:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b216fcb1a881908edeadc639de31ae |
completed | March 12, 2026, 1:29 a.m. |
Created at: March 8, 2026, 3:04 p.m.