Triple
T15777787
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wazwan |
E382532
|
entity |
| Predicate | preparationBy |
P48513
|
FINISHED |
| Object |
Waza
Waza is a traditional Kashmiri master chef renowned for preparing the elaborate multi-course feast known as Wazwan.
|
E1177409
|
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: Waza | Statement: [Wazwan, preparationBy, Waza]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Waza Context triple: [Wazwan, preparationBy, Waza]
-
A.
Kasindi
Kasindi is a border town in eastern Democratic Republic of the Congo, located near Uganda and serving as an important regional trade and transport hub.
-
B.
Takrur
Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
-
C.
Wajir
Wajir is a major town in northeastern Kenya that serves as an important commercial and administrative center in a predominantly arid, pastoralist region.
-
D.
Nzera
Nzera is a settlement located within Tanzania’s Geita Region in East Africa.
-
E.
Ngazidja
Ngazidja, also known as Grande Comore, is the largest island of the Comoros archipelago in the Indian Ocean and home to the nation’s capital.
- 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: Waza Triple: [Wazwan, preparationBy, Waza]
Generated description
Waza is a traditional Kashmiri master chef renowned for preparing the elaborate multi-course feast known as Wazwan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Waza Target entity description: Waza is a traditional Kashmiri master chef renowned for preparing the elaborate multi-course feast known as Wazwan.
-
A.
Kasindi
Kasindi is a border town in eastern Democratic Republic of the Congo, located near Uganda and serving as an important regional trade and transport hub.
-
B.
Takrur
Takrur was an early West African kingdom located in the Senegal River valley, known for its role in trans-Saharan trade and its early adoption of Islam.
-
C.
Wajir
Wajir is a major town in northeastern Kenya that serves as an important commercial and administrative center in a predominantly arid, pastoralist region.
-
D.
Nzera
Nzera is a settlement located within Tanzania’s Geita Region in East Africa.
-
E.
Ngazidja
Ngazidja, also known as Grande Comore, is the largest island of the Comoros archipelago in the Indian Ocean and home to the nation’s capital.
- 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_69d86da09a10819082fe9797b23e4664 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e05199cd8881909462462cec34d35a |
completed | April 16, 2026, 3:03 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ff909d7b7c81908b62faa2ab378fad |
completed | May 9, 2026, 7:53 p.m. |
| NEDg | Description generation | batch_69ff9414408c8190903421d28519d9e6 |
completed | May 9, 2026, 8:07 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69ff9498642081909fd617a327b4c704 |
completed | May 9, 2026, 8:10 p.m. |
Created at: April 10, 2026, 4:47 a.m.