Triple
T16998222
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Janna Little Ryan |
E412371
|
entity |
| Predicate | givenName |
P17
|
FINISHED |
| Object |
Janna
Janna is an American tax attorney best known as the wife of former U.S. Speaker of the House and 2012 vice-presidential nominee Paul Ryan.
|
E1245162
|
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: Janna | Statement: [Janna Little Ryan, givenName, Janna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Janna Context triple: [Janna Little Ryan, givenName, Janna]
-
A.
Janna Ordonia
Janna Ordonia is a mischievous, troublemaking human girl in *Star vs. the Forces of Evil*, known for her love of the occult, pranks, and deadpan humor.
-
B.
Rainelle
Rainelle is a small town located in western Greenbrier County, West Virginia, historically tied to the lumber industry and the surrounding Appalachian region.
-
C.
Channah
Channah is a given name, often considered a variant of the Hebrew name Hannah, traditionally associated with grace or favor.
-
D.
Xandra
Xandra is a shortened, informal given name derived from Alexandra, often used as a modern, distinctive feminine name.
-
E.
Damara
The Damara are an indigenous ethnic group of Namibia known for their distinct language, rich oral traditions, and historical presence in the country’s northwestern regions.
- 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: Janna Triple: [Janna Little Ryan, givenName, Janna]
Generated description
Janna is an American tax attorney best known as the wife of former U.S. Speaker of the House and 2012 vice-presidential nominee Paul Ryan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Janna Target entity description: Janna is an American tax attorney best known as the wife of former U.S. Speaker of the House and 2012 vice-presidential nominee Paul Ryan.
-
A.
Janna Ordonia
Janna Ordonia is a mischievous, troublemaking human girl in *Star vs. the Forces of Evil*, known for her love of the occult, pranks, and deadpan humor.
-
B.
Rainelle
Rainelle is a small town located in western Greenbrier County, West Virginia, historically tied to the lumber industry and the surrounding Appalachian region.
-
C.
Channah
Channah is a given name, often considered a variant of the Hebrew name Hannah, traditionally associated with grace or favor.
-
D.
Xandra
Xandra is a shortened, informal given name derived from Alexandra, often used as a modern, distinctive feminine name.
-
E.
Damara
The Damara are an indigenous ethnic group of Namibia known for their distinct language, rich oral traditions, and historical presence in the country’s northwestern regions.
- 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_69d886cb581c8190ab05f4b429c9cd85 |
completed | April 10, 2026, 5:12 a.m. |
| NER | Named-entity recognition | batch_69e3d37c16d081908ea5e25c992cb254 |
completed | April 18, 2026, 6:54 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a00dc18e6988190b42b3d251cf00b98 |
completed | May 10, 2026, 7:27 p.m. |
| NEDg | Description generation | batch_6a0114d68c8481909111bfab22882bb2 |
completed | May 10, 2026, 11:29 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0118ba68408190b242154c40461f21 |
completed | May 10, 2026, 11:46 p.m. |
Created at: April 10, 2026, 5:32 a.m.