Triple
T8065005
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jaisalmer Fort |
E188220
|
entity |
| Predicate | hasGate |
P4365
|
FINISHED |
| Object |
Hawa Pol
Hawa Pol is one of the main historic gateways of Jaisalmer Fort in Rajasthan, India, known for its traditional Rajput architecture and strategic entrance role.
|
E709849
|
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: Hawa Pol | Statement: [Jaisalmer Fort, hasGate, Hawa Pol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Hawa Pol Context triple: [Jaisalmer Fort, hasGate, Hawa Pol]
-
A.
Haga Nygata
Haga Nygata is a historic, cobblestoned main street in Gothenburg’s Haga district, known for its preserved wooden houses, cafés, and small shops.
-
B.
Fairuza
Fairuza is a feminine given name most famously borne by American actress Fairuza Balk.
-
C.
Haya
Haya is a feminine given name of Arabic origin, commonly used in the Middle East and among Arabic-speaking communities.
-
D.
Grace Wahu
Grace Wahu was the first wife of Jomo Kenyatta, Kenya’s founding president, and a notable early figure in his personal and political life.
-
E.
Mona Rudao
Mona Rudao was a Seediq indigenous chieftain and resistance leader in Taiwan who led an uprising against Japanese colonial rule in 1930.
- 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: Hawa Pol Triple: [Jaisalmer Fort, hasGate, Hawa Pol]
Generated description
Hawa Pol is one of the main historic gateways of Jaisalmer Fort in Rajasthan, India, known for its traditional Rajput architecture and strategic entrance role.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Hawa Pol Target entity description: Hawa Pol is one of the main historic gateways of Jaisalmer Fort in Rajasthan, India, known for its traditional Rajput architecture and strategic entrance role.
-
A.
Haga Nygata
Haga Nygata is a historic, cobblestoned main street in Gothenburg’s Haga district, known for its preserved wooden houses, cafés, and small shops.
-
B.
Fairuza
Fairuza is a feminine given name most famously borne by American actress Fairuza Balk.
-
C.
Haya
Haya is a feminine given name of Arabic origin, commonly used in the Middle East and among Arabic-speaking communities.
-
D.
Grace Wahu
Grace Wahu was the first wife of Jomo Kenyatta, Kenya’s founding president, and a notable early figure in his personal and political life.
-
E.
Mona Rudao
Mona Rudao was a Seediq indigenous chieftain and resistance leader in Taiwan who led an uprising against Japanese colonial rule in 1930.
- 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_69ca82b42674819086840efea12478e5 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb3fd07fd08190a3b61cb3369ee6a6 |
completed | March 31, 2026, 3:30 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc63de88fc8190ac2c46edca324cec |
completed | April 1, 2026, 12:16 a.m. |
| NEDg | Description generation | batch_69cc6544909c819097529c279926e9cd |
completed | April 1, 2026, 12:22 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc686f343081908f56809d297fdac0 |
completed | April 1, 2026, 12:35 a.m. |
Created at: March 30, 2026, 5:26 p.m.