Triple
T6849732
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Beryl |
E157983
|
entity |
| Predicate | hasNotableBearer |
P458
|
FINISHED |
| Object |
Beryl Clark
Beryl Clark was an American football player best known for playing as a halfback for the University of Oklahoma in the late 1930s.
|
E688154
|
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: Beryl Clark | Statement: [Beryl, hasNotableBearer, Beryl Clark]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Beryl Clark Context triple: [Beryl, hasNotableBearer, Beryl Clark]
-
A.
Beryl Mercer
Beryl Mercer was a British-born character actress known for her maternal and supporting roles in early 20th-century stage and Hollywood films.
-
B.
Beryl Penrose
Beryl Penrose was an Australian tennis player best known for winning the women’s singles title at the 1955 Australian Championships.
-
C.
Beryl Rawson
Beryl Rawson was an Australian classicist and historian renowned for her influential research on the social history of ancient Rome, particularly Roman family life and childhood.
-
D.
Aileen Britton
Aileen Britton was an Australian actress known for her work in film, television, and theatre during the mid-20th century.
-
E.
Marjorie Wren
Marjorie Wren was the second wife of Scottish editor and military officer Hugh Alexander Pollock, known primarily through her marriage to him.
- 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: Beryl Clark Triple: [Beryl, hasNotableBearer, Beryl Clark]
Generated description
Beryl Clark was an American football player best known for playing as a halfback for the University of Oklahoma in the late 1930s.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Beryl Clark Target entity description: Beryl Clark was an American football player best known for playing as a halfback for the University of Oklahoma in the late 1930s.
-
A.
Beryl Mercer
Beryl Mercer was a British-born character actress known for her maternal and supporting roles in early 20th-century stage and Hollywood films.
-
B.
Beryl Penrose
Beryl Penrose was an Australian tennis player best known for winning the women’s singles title at the 1955 Australian Championships.
-
C.
Beryl Rawson
Beryl Rawson was an Australian classicist and historian renowned for her influential research on the social history of ancient Rome, particularly Roman family life and childhood.
-
D.
Aileen Britton
Aileen Britton was an Australian actress known for her work in film, television, and theatre during the mid-20th century.
-
E.
Marjorie Wren
Marjorie Wren was the second wife of Scottish editor and military officer Hugh Alexander Pollock, known primarily through her marriage to him.
- 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_69c6882fae988190864cbba788c5ebb4 |
completed | March 27, 2026, 1:37 p.m. |
| NER | Named-entity recognition | batch_69c6d84acb288190a67d974197ecab2f |
completed | March 27, 2026, 7:19 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c8d67da5708190973ac88aa67e32b1 |
completed | March 29, 2026, 7:36 a.m. |
| NEDg | Description generation | batch_69c8d6e89c5081908638fdfa24abf4dc |
completed | March 29, 2026, 7:38 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69c8d740c4848190b34f4cf7ad708592 |
completed | March 29, 2026, 7:39 a.m. |
Created at: March 27, 2026, 2:20 p.m.