Triple
T2021200
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sarah Hughes |
E44108
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object |
Laura Hughes
Laura Hughes is known as the sister of American Olympic figure skater Sarah Hughes.
|
E359486
|
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: Laura Hughes | Statement: [Sarah Hughes, sibling, Laura Hughes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Laura Hughes Context triple: [Sarah Hughes, sibling, Laura Hughes]
-
A.
Genevieve Hughes
Genevieve Hughes is known primarily as the sister of American Olympic figure skating champion Sarah Hughes.
-
B.
Wendy Hughes
Wendy Hughes was an acclaimed Australian actress known for her versatile performances in film, television, and theatre from the 1970s onward.
-
C.
Laura Jarrett
Laura Jarrett is an American attorney and journalist known for her work as a legal correspondent on major U.S. news networks.
-
D.
Helen Hughes
Helen Hughes was a daughter of Charles Evans Hughes, the prominent American statesman who served as both U.S. Secretary of State and Chief Justice of the Supreme Court.
-
E.
Laura Jennings
Laura Jennings is a film editor best known for her work on major action and science fiction movies, including the Tom Cruise–led blockbuster "Edge of Tomorrow."
- 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: Laura Hughes Triple: [Sarah Hughes, sibling, Laura Hughes]
Generated description
Laura Hughes is known as the sister of American Olympic figure skater Sarah Hughes.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Laura Hughes Target entity description: Laura Hughes is known as the sister of American Olympic figure skater Sarah Hughes.
-
A.
Genevieve Hughes
Genevieve Hughes is known primarily as the sister of American Olympic figure skating champion Sarah Hughes.
-
B.
Wendy Hughes
Wendy Hughes was an acclaimed Australian actress known for her versatile performances in film, television, and theatre from the 1970s onward.
-
C.
Laura Jarrett
Laura Jarrett is an American attorney and journalist known for her work as a legal correspondent on major U.S. news networks.
-
D.
Helen Hughes
Helen Hughes was a daughter of Charles Evans Hughes, the prominent American statesman who served as both U.S. Secretary of State and Chief Justice of the Supreme Court.
-
E.
Laura Jennings
Laura Jennings is a film editor best known for her work on major action and science fiction movies, including the Tom Cruise–led blockbuster "Edge of Tomorrow."
- 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_69a8891201bc8190aca837be6de41579 |
completed | March 4, 2026, 7:33 p.m. |
| NER | Named-entity recognition | batch_69abb8ee02dc81908fec9fd8df7a4f40 |
completed | March 7, 2026, 5:34 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3606f413c8190b3f8e5e8fcaa6878 |
completed | March 13, 2026, 12:55 a.m. |
| NEDg | Description generation | batch_69b3614702348190bd35c37d2059312f |
completed | March 13, 2026, 12:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b362451b848190a2fe80a17ab8f9c3 |
completed | March 13, 2026, 1:03 a.m. |
Created at: March 4, 2026, 7:38 p.m.