Triple
T19790651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Temeke |
E475399
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Tandika
Tandika is a ward and urban neighborhood located within the Temeke District of Dar es Salaam, Tanzania.
|
E1395221
|
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: Tandika | Statement: [Temeke, contains, Tandika]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tandika Context triple: [Temeke, contains, Tandika]
-
A.
Mandika
Mandika is an alternative name for the Mandinka, a major West African ethnic group known for their rich cultural traditions and historical role in the Mali Empire.
-
B.
Scrawl
Scrawl is an American indie rock band known for its raw, emotionally direct songs and influential role in the 1980s–1990s underground music scene.
-
C.
Scribble
Scribble is an Apple Pencil feature on iPadOS that converts handwritten input into typed text in real time across compatible apps.
-
D.
Teclea
Teclea is a genus of flowering plants in the citrus family Rutaceae, native to parts of Africa and known for its aromatic foliage.
-
E.
Tupian
Tupian is a major indigenous language family of South America, encompassing numerous related languages spoken primarily in Brazil and neighboring regions.
- 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: Tandika Triple: [Temeke, contains, Tandika]
Generated description
Tandika is a ward and urban neighborhood located within the Temeke District of Dar es Salaam, Tanzania.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tandika Target entity description: Tandika is a ward and urban neighborhood located within the Temeke District of Dar es Salaam, Tanzania.
-
A.
Mandika
Mandika is an alternative name for the Mandinka, a major West African ethnic group known for their rich cultural traditions and historical role in the Mali Empire.
-
B.
Scrawl
Scrawl is an American indie rock band known for its raw, emotionally direct songs and influential role in the 1980s–1990s underground music scene.
-
C.
Scribble
Scribble is an Apple Pencil feature on iPadOS that converts handwritten input into typed text in real time across compatible apps.
-
D.
Teclea
Teclea is a genus of flowering plants in the citrus family Rutaceae, native to parts of Africa and known for its aromatic foliage.
-
E.
Tupian
Tupian is a major indigenous language family of South America, encompassing numerous related languages spoken primarily in Brazil and neighboring regions.
- 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_69d8e51b014081908b263e167370529a |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e653c217bc819092c517b27ca22087 |
completed | April 20, 2026, 4:26 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a07c4fff3548190a069b665c0885627 |
completed | May 16, 2026, 1:14 a.m. |
| NEDg | Description generation | batch_6a07c580b3108190bcc64fe1f479d7c4 |
completed | May 16, 2026, 1:16 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a07c5e7a5d08190b6a24f66ff966cec |
completed | May 16, 2026, 1:18 a.m. |
Created at: April 10, 2026, 1:49 p.m.