Triple
T12486431
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Clay Smith Breckinridge |
E298443
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Smith
Smith is a given name that, in this context, forms part of the full name of Mary Clay Smith Breckinridge.
|
E30542
|
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: Smith | Statement: [Mary Clay Smith Breckinridge, givenName, Smith]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Smith Context triple: [Mary Clay Smith Breckinridge, givenName, Smith]
-
A.
John
John is the given name of the late American comedian and actor John Belushi, famed for his work on "Saturday Night Live" and in films like "Animal House" and "The Blues Brothers."
-
B.
John
John Stallworth is a former American football wide receiver best known for his Hall of Fame career with the Pittsburgh Steelers during their 1970s dynasty.
-
C.
John
John I, Count of Holland, was a medieval nobleman who ruled the County of Holland at the turn of the 14th century.
-
D.
John
John Cicero was a late 15th-century Elector of Brandenburg from the House of Hohenzollern who helped consolidate the territory’s political and administrative structures within the Holy Roman Empire.
-
E.
John
John Brabourne was a British film and television producer and peer, known for producing works such as the 1979 adaptation of "Murder on the Orient Express."
- 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: Smith Triple: [Mary Clay Smith Breckinridge, givenName, Smith]
Generated description
Smith is a given name that, in this context, forms part of the full name of Mary Clay Smith Breckinridge.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Smith Target entity description: Smith is a given name that, in this context, forms part of the full name of Mary Clay Smith Breckinridge.
-
A.
Smith
chosen
Smith is a common English surname borne by numerous notable individuals across diverse fields such as politics, arts, sports, and academia.
-
B.
John
John is the given name of John Albert William Spencer-Churchill, a British aristocrat and 10th Duke of Marlborough.
-
C.
John
John I, Count of Holland, was a medieval nobleman who ruled the County of Holland at the turn of the 14th century.
-
D.
John
John McDowell is a prominent South African-born philosopher known for his influential work in epistemology, philosophy of mind, and ethics.
-
E.
John
John Cicero was a late 15th-century Elector of Brandenburg from the House of Hohenzollern who helped consolidate the territory’s political and administrative structures within the Holy Roman Empire.
- F. None of above.
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_69d6ada377208190a36011199a4d8558 |
completed | April 8, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69d94de077bc81908b5ff057a1bf2b4f |
completed | April 10, 2026, 7:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f63f2b5ed481909ead4f5b96d44064 |
completed | May 2, 2026, 6:15 p.m. |
| NEDg | Description generation | batch_69f6401199408190ad2657802afd93c9 |
completed | May 2, 2026, 6:18 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f6416ba1bc8190a772bffe4d83ec15 |
completed | May 2, 2026, 6:24 p.m. |
Created at: April 8, 2026, 9:56 p.m.