Triple
T19156928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Likati Health Zone |
E468949
|
entity |
| Predicate | hasAdministrativeCenter |
P1474
|
FINISHED |
| Object |
Likati
Likati is a town in the northern Democratic Republic of the Congo that serves as a local administrative and commercial center.
|
E1362386
|
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: Likati | Statement: [Likati Health Zone, hasAdministrativeCenter, Likati]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Likati Context triple: [Likati Health Zone, hasAdministrativeCenter, Likati]
-
A.
Luqa
Luqa is a village in the Central Region of Malta best known for hosting the island’s main international airport, Malta International Airport.
-
B.
Landana
Landana is a coastal town in Angola’s Cabinda exclave, historically known as a regional trading and missionary center.
-
C.
Marakata
Marakata was a Balinese king of the Warmadewa dynasty who ruled in the early 11th century, known for continuing the consolidation and development of the Balinese kingdom.
-
D.
Liluah
Liluah is a suburban locality in the Howrah district of West Bengal, India, known for its residential areas and railway facilities near Kolkata.
-
E.
Makrakomi
Makrakomi is a town and municipality in Central Greece, situated in the regional unit of Phthiotis.
- 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: Likati Triple: [Likati Health Zone, hasAdministrativeCenter, Likati]
Generated description
Likati is a town in the northern Democratic Republic of the Congo that serves as a local administrative and commercial center.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Likati Target entity description: Likati is a town in the northern Democratic Republic of the Congo that serves as a local administrative and commercial center.
-
A.
Luqa
Luqa is a village in the Central Region of Malta best known for hosting the island’s main international airport, Malta International Airport.
-
B.
Landana
Landana is a coastal town in Angola’s Cabinda exclave, historically known as a regional trading and missionary center.
-
C.
Marakata
Marakata was a Balinese king of the Warmadewa dynasty who ruled in the early 11th century, known for continuing the consolidation and development of the Balinese kingdom.
-
D.
Liluah
Liluah is a suburban locality in the Howrah district of West Bengal, India, known for its residential areas and railway facilities near Kolkata.
-
E.
Makrakomi
Makrakomi is a town and municipality in Central Greece, situated in the regional unit of Phthiotis.
- 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_69d8dd084ff48190ac0f8c46ee722629 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5eeb9cf9081908b17073755e83554 |
completed | April 20, 2026, 9:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a06f8a7e1fc81909e72a9c40d0528e4 |
completed | May 15, 2026, 10:42 a.m. |
| NEDg | Description generation | batch_6a06f91fe48081909cb332dca4bdb1f4 |
completed | May 15, 2026, 10:44 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a06f9a5bddc8190acb60a66c5fc3536 |
completed | May 15, 2026, 10:47 a.m. |
Created at: April 10, 2026, 12:06 p.m.