Triple
T22689266
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Banjarese |
E561004
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object |
Banjar Hulu
Banjar Hulu is an upstream regional dialect of the Banjarese language spoken primarily in the interior areas of South Kalimantan, Indonesia.
|
E1548820
|
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 Hulu | Statement: [Banjarese, hasDialect, Banjar Hulu]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Banjar Hulu Context triple: [Banjarese, hasDialect, Banjar Hulu]
-
A.
Lubuk Basung
Lubuk Basung is the administrative and economic center of Agam Regency in West Sumatra, Indonesia.
-
B.
Lubuk Alung
Lubuk Alung is a town in West Sumatra, Indonesia, known as an important local administrative and transportation hub within Padang Pariaman Regency.
-
C.
Batusangkar
Batusangkar is a historic town in West Sumatra, Indonesia, known as a cultural center of the Minangkabau people and gateway to the scenic Minangkabau Highlands.
-
D.
Lembah Jaya
Lembah Jaya is a residential and suburban area within the municipality of Ampang Jaya in Selangor, Malaysia.
-
E.
Batang Baleh
Batang Baleh is a significant river in Sarawak, Malaysia, known for flowing through remote forested areas and supporting local indigenous communities and logging activities.
- 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 Hulu Triple: [Banjarese, hasDialect, Banjar Hulu]
Generated description
Banjar Hulu is an upstream regional dialect of the Banjarese language spoken primarily in the interior areas of South Kalimantan, Indonesia.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Banjar Hulu Target entity description: Banjar Hulu is an upstream regional dialect of the Banjarese language spoken primarily in the interior areas of South Kalimantan, Indonesia.
-
A.
Lubuk Basung
Lubuk Basung is the administrative and economic center of Agam Regency in West Sumatra, Indonesia.
-
B.
Lubuk Alung
Lubuk Alung is a town in West Sumatra, Indonesia, known as an important local administrative and transportation hub within Padang Pariaman Regency.
-
C.
Batusangkar
Batusangkar is a historic town in West Sumatra, Indonesia, known as a cultural center of the Minangkabau people and gateway to the scenic Minangkabau Highlands.
-
D.
Lembah Jaya
Lembah Jaya is a residential and suburban area within the municipality of Ampang Jaya in Selangor, Malaysia.
-
E.
Batang Baleh
Batang Baleh is a significant river in Sarawak, Malaysia, known for flowing through remote forested areas and supporting local indigenous communities and logging activities.
- 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_69e2454d71b48190a1f80af9f82b6fcf |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1789931148190925ce9038c16413b |
completed | April 29, 2026, 3:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0b73f90304819084b6c4c944cbf504 |
completed | May 18, 2026, 8:18 p.m. |
| NEDg | Description generation | batch_6a0b7505c99081908a9faac30451e6e8 |
completed | May 18, 2026, 8:22 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0b761510b48190a09722be3fca7e93 |
completed | May 18, 2026, 8:27 p.m. |
Created at: April 17, 2026, 3:13 p.m.