Triple
T1385219
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | West Java |
E29829
|
entity |
| Predicate | hasMajorCity |
P316
|
FINISHED |
| Object |
Banjar
Banjar is a city in the eastern part of West Java, Indonesia, known as a regional transit hub connecting West Java with Central Java.
|
E157769
|
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: Banjar | Statement: [West Java, hasMajorCity, Banjar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Banjar Context triple: [West Java, hasMajorCity, Banjar]
-
A.
Mangkasar
Mangkasar is the historical name for Makassar, a major port city and cultural center on the island of Sulawesi in Indonesia.
-
B.
Tasikmalaya
Tasikmalaya is a significant city in West Java, Indonesia, known as an important cultural and economic hub for the Sundanese people.
-
C.
Bangkalan
Bangkalan is a major urban center and regency on the western part of Madura Island in Indonesia, serving as an important gateway between Madura and Java.
-
D.
Sampang
Sampang is a coastal city and regency capital on Madura Island in East Java, Indonesia, known for its traditional Madurese culture and agriculture-based economy.
-
E.
Blitar
Blitar is a city in East Java, Indonesia, best known as the hometown and final resting place of the country’s first president, Sukarno.
- 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: Banjar Triple: [West Java, hasMajorCity, Banjar]
Generated description
Banjar is a city in the eastern part of West Java, Indonesia, known as a regional transit hub connecting West Java with Central Java.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Banjar Target entity description: Banjar is a city in the eastern part of West Java, Indonesia, known as a regional transit hub connecting West Java with Central Java.
-
A.
Mangkasar
Mangkasar is the historical name for Makassar, a major port city and cultural center on the island of Sulawesi in Indonesia.
-
B.
Tasikmalaya
Tasikmalaya is a significant city in West Java, Indonesia, known as an important cultural and economic hub for the Sundanese people.
-
C.
Bangkalan
Bangkalan is a major urban center and regency on the western part of Madura Island in Indonesia, serving as an important gateway between Madura and Java.
-
D.
Sampang
Sampang is a coastal city and regency capital on Madura Island in East Java, Indonesia, known for its traditional Madurese culture and agriculture-based economy.
-
E.
Blitar
Blitar is a city in East Java, Indonesia, best known as the hometown and final resting place of the country’s first president, Sukarno.
- 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_69a498dc92f8819094a1108f8ac90f43 |
completed | March 1, 2026, 7:51 p.m. |
| NER | Named-entity recognition | batch_69a4c33896548190b44f70c9aaaed9b6 |
completed | March 1, 2026, 10:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69acd48e046c8190bc4820d6c4ce907d |
completed | March 8, 2026, 1:44 a.m. |
| NEDg | Description generation | batch_69acd57bf87c8190ad22de7b5636fcfc |
completed | March 8, 2026, 1:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69acd5e54e98819084ba0022ca64ff43 |
completed | March 8, 2026, 1:50 a.m. |
Created at: March 1, 2026, 7:59 p.m.