Triple
T4795279
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ajanta Caves |
E106694
|
entity |
| Predicate | discoveredBy |
P412
|
FINISHED |
| Object |
John Smith
John Smith was a 19th-century British officer credited with bringing the Ajanta Caves to modern attention after rediscovering them in 1819.
|
E470455
|
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: John Smith | Statement: [Ajanta Caves, discoveredBy, John Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Smith Context triple: [Ajanta Caves, discoveredBy, John Smith]
-
A.
John
John "Stuffy" McInnis was an American Major League Baseball first baseman best known as a member of Connie Mack’s Philadelphia Athletics dynasty in the early 20th century.
-
B.
John
John is the given name of John Frank Stevens, the American civil engineer best known for his pivotal role in the construction of the Panama Canal.
-
C.
John
John Parke Custis was the son of Martha Washington and stepson of George Washington, known as a Virginia planter and member of the colonial gentry.
-
D.
John
John is the given name of Sir John Copley, a titled individual likely known for his status and contributions within British society.
-
E.
John
John is the given name of American politician and diplomat John Kerry, a former U.S. Secretary of State and Democratic presidential nominee.
- 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: John Smith Triple: [Ajanta Caves, discoveredBy, John Smith]
Generated description
John Smith was a 19th-century British officer credited with bringing the Ajanta Caves to modern attention after rediscovering them in 1819.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Smith Target entity description: John Smith was a 19th-century British officer credited with bringing the Ajanta Caves to modern attention after rediscovering them in 1819.
-
A.
John Smith
John Smith was an English soldier, explorer, and leader who played a pivotal role in the establishment and survival of the Jamestown colony in early colonial Virginia.
-
B.
John Smith
John Smith is a high-ranking Nazi official in the alternate-history television series "The Man in the High Castle," whose loyalty, ambition, and moral conflicts drive much of the show's central drama.
-
C.
John
John is the husband of Martha Rainsborough.
-
D.
John
John W. Tukey was an influential American mathematician and statistician known for pioneering exploratory data analysis and coining the term "bit."
-
E.
John
John is the given name of Colonel John Quincy, an American military officer and politician after whom John Quincy Adams was named.
- 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_69bd43f591c881909e5a532388b0f3f3 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6609e9888190b49f99bb9fb2279d |
completed | March 20, 2026, 3:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be43f512e0819086cc33009cd45c9a |
completed | March 21, 2026, 7:08 a.m. |
| NEDg | Description generation | batch_69be44cb99ac819089bbb941709a93c4 |
completed | March 21, 2026, 7:12 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be451e8d7c81908d856e7966daa5fe |
completed | March 21, 2026, 7:13 a.m. |
Created at: March 20, 2026, 1:22 p.m.