Triple
T22988924
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gibran Rakabuming Raka |
E571993
|
entity |
| Predicate | founded |
P104
|
FINISHED |
| Object |
Markobar
Markobar is an Indonesian dessert brand and chain best known for its creative martabak (sweet stuffed pancake) variations, popularized by Gibran Rakabuming Raka.
|
E1565061
|
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: Markobar | Statement: [Gibran Rakabuming Raka, founded, Markobar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Markobar Context triple: [Gibran Rakabuming Raka, founded, Markobar]
-
A.
Japeri
Japeri is a municipality in the state of Rio de Janeiro, Brazil, known for its location in the Baixada Fluminense region and its role as a railway hub.
-
B.
Bariadi
Bariadi is a town in northern Tanzania that serves as an important local administrative and commercial center.
-
C.
Barpak
Barpak is a mountainous village in central Nepal known as the epicenter of the devastating 2015 Gorkha earthquake and for its scenic Himalayan landscapes.
-
D.
Barmal
Barmal is a town in southeastern Afghanistan known for its location in Paktika Province near the border with Pakistan.
-
E.
Barchon
Barchon is a village in the municipality of Blegny in the province of Liège, Belgium.
- 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: Markobar Triple: [Gibran Rakabuming Raka, founded, Markobar]
Generated description
Markobar is an Indonesian dessert brand and chain best known for its creative martabak (sweet stuffed pancake) variations, popularized by Gibran Rakabuming Raka.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Markobar Target entity description: Markobar is an Indonesian dessert brand and chain best known for its creative martabak (sweet stuffed pancake) variations, popularized by Gibran Rakabuming Raka.
-
A.
Japeri
Japeri is a municipality in the state of Rio de Janeiro, Brazil, known for its location in the Baixada Fluminense region and its role as a railway hub.
-
B.
Bariadi
Bariadi is a town in northern Tanzania that serves as an important local administrative and commercial center.
-
C.
Barpak
Barpak is a mountainous village in central Nepal known as the epicenter of the devastating 2015 Gorkha earthquake and for its scenic Himalayan landscapes.
-
D.
Barmal
Barmal is a town in southeastern Afghanistan known for its location in Paktika Province near the border with Pakistan.
-
E.
Barchon
Barchon is a village in the municipality of Blegny in the province of Liège, Belgium.
- 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_69e245b535808190adef8a9df3c584db |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f182ea55cc8190b64b722ce8c45b53 |
completed | April 29, 2026, 4:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0bd3792ad0819094416aebc79ab1f7 |
completed | May 19, 2026, 3:05 a.m. |
| NEDg | Description generation | batch_6a0bd40988808190add22943683b7a1b |
completed | May 19, 2026, 3:07 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0bd503b1588190979b9895327a3475 |
completed | May 19, 2026, 3:12 a.m. |
Created at: April 17, 2026, 3:49 p.m.