Triple
T8159305
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Junagarh Fort |
E190532
|
entity |
| Predicate | mainGate |
P4365
|
FINISHED |
| Object |
Karan Pol
Karan Pol is a historic gateway that serves as one of the principal entrances to Junagarh Fort in Bikaner, Rajasthan, India.
|
E715257
|
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: Karan Pol | Statement: [Junagarh Fort, mainGate, Karan Pol]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Karan Pol Context triple: [Junagarh Fort, mainGate, Karan Pol]
-
A.
Madhan Karky
Madhan Karky is an Indian lyricist, dialogue writer, and technologist known for his innovative work in Tamil cinema and contributions to major films like Baahubali: The Beginning.
-
B.
Dani Karavan
Dani Karavan was an Israeli sculptor and environmental artist renowned for his large-scale site-specific memorials and public artworks that integrate landscape, architecture, and history.
-
C.
Buz Kohan
Buz Kohan is an American television writer, producer, and composer known for his work on variety shows and specials.
-
D.
Nez Khammal
Nez Khammal is a British music video director known for his visually distinctive work with prominent hip-hop and pop artists.
-
E.
Kara Osman
Kara Osman, better known as Osman I, was the founder and first ruler of the Ottoman Empire in the late 13th and early 14th centuries.
- 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: Karan Pol Triple: [Junagarh Fort, mainGate, Karan Pol]
Generated description
Karan Pol is a historic gateway that serves as one of the principal entrances to Junagarh Fort in Bikaner, Rajasthan, India.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Karan Pol Target entity description: Karan Pol is a historic gateway that serves as one of the principal entrances to Junagarh Fort in Bikaner, Rajasthan, India.
-
A.
Madhan Karky
Madhan Karky is an Indian lyricist, dialogue writer, and technologist known for his innovative work in Tamil cinema and contributions to major films like Baahubali: The Beginning.
-
B.
Dani Karavan
Dani Karavan was an Israeli sculptor and environmental artist renowned for his large-scale site-specific memorials and public artworks that integrate landscape, architecture, and history.
-
C.
Buz Kohan
Buz Kohan is an American television writer, producer, and composer known for his work on variety shows and specials.
-
D.
Nez Khammal
Nez Khammal is a British music video director known for his visually distinctive work with prominent hip-hop and pop artists.
-
E.
Kara Osman
Kara Osman, better known as Osman I, was the founder and first ruler of the Ottoman Empire in the late 13th and early 14th centuries.
- 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_69ca82bfeb6481909d07b91b5cf69f59 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb455213f08190a4327a2116c7381f |
completed | March 31, 2026, 3:53 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ccbf21ab2c8190af23b4a3a4bdb543 |
completed | April 1, 2026, 6:45 a.m. |
| NEDg | Description generation | batch_69ccc24c5684819093a4f58616122675 |
completed | April 1, 2026, 6:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ccc38e85bc8190b0f4b2435a385f47 |
completed | April 1, 2026, 7:04 a.m. |
Created at: March 30, 2026, 5:38 p.m.