Triple
T6753770
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sara language |
E154401
|
entity |
| Predicate | hasDialect |
P4251
|
FINISHED |
| Object |
Ngam
Ngam is a dialect of the Sara language spoken by communities in parts of Central Africa, particularly in Chad and the surrounding region.
|
E615472
|
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: Ngam | Statement: [Sara language, hasDialect, Ngam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ngam Context triple: [Sara language, hasDialect, Ngam]
-
A.
Thommanon
Thommanon is a small 12th-century Hindu temple in the Angkor region of Cambodia, noted for its well-preserved sandstone carvings and classical Khmer architecture.
-
B.
Tasiwit
Tasiwit is an alternative name for Siwi, a Berber language spoken in Egypt’s Siwa Oasis.
-
C.
Phimeanakas
Phimeanakas is an ancient Hindu temple within Angkor Thom in Cambodia, built in a stepped pyramid style and historically associated with the royal palace of the Khmer Empire.
-
D.
Ngamprah
Ngamprah is an administrative town in West Java, Indonesia, serving as the governmental and economic center of West Bandung Regency.
-
E.
Udomlya
Udomlya is a town in western Russia known for its proximity to the Kalinin Nuclear Power Plant and its location within the Tver Oblast region.
- 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: Ngam Triple: [Sara language, hasDialect, Ngam]
Generated description
Ngam is a dialect of the Sara language spoken by communities in parts of Central Africa, particularly in Chad and the surrounding region.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Ngam Target entity description: Ngam is a dialect of the Sara language spoken by communities in parts of Central Africa, particularly in Chad and the surrounding region.
-
A.
Thommanon
Thommanon is a small 12th-century Hindu temple in the Angkor region of Cambodia, noted for its well-preserved sandstone carvings and classical Khmer architecture.
-
B.
Tasiwit
Tasiwit is an alternative name for Siwi, a Berber language spoken in Egypt’s Siwa Oasis.
-
C.
Phimeanakas
Phimeanakas is an ancient Hindu temple within Angkor Thom in Cambodia, built in a stepped pyramid style and historically associated with the royal palace of the Khmer Empire.
-
D.
Ngamprah
Ngamprah is an administrative town in West Java, Indonesia, serving as the governmental and economic center of West Bandung Regency.
-
E.
Udomlya
Udomlya is a town in western Russia known for its proximity to the Kalinin Nuclear Power Plant and its location within the Tver Oblast region.
- 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_69c6880fd5808190be684854081e27dd |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d1f32fa08190bb23dc24fef14c8d |
completed | March 27, 2026, 6:52 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c70b1c4594819084716e21b16191e3 |
completed | March 27, 2026, 10:56 p.m. |
| NEDg | Description generation | batch_69c70c4111848190906b0e43cf4ae325 |
completed | March 27, 2026, 11:01 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c70cbb8644819091a8a9c061dfd605 |
completed | March 27, 2026, 11:03 p.m. |
Created at: March 27, 2026, 2:11 p.m.