Triple
T21901858
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Jolly Fellows |
E540828
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Marian Bering
Marian Bering was an actress known for her role in the Soviet musical comedy film "Jolly Fellows."
|
E1508356
|
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: Marian Bering | Statement: [Jolly Fellows, starring, Marian Bering]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Marian Bering Context triple: [Jolly Fellows, starring, Marian Bering]
-
A.
Kathleen Bering
Kathleen Bering was the wife of silent film and stage actor Creighton Hale.
-
B.
Marianne Stenshagen
Marianne Stenshagen is a Norwegian speed skater who has competed at the international level representing Norway.
-
C.
Alison Arngrim
Alison Arngrim is an American actress and author best known for her iconic portrayal of the scheming Nellie Oleson on the classic television series "Little House on the Prairie."
-
D.
Margaret Halstan
Margaret Halstan was an English stage and film actress active in the late 19th and early 20th centuries, known for her refined character roles.
-
E.
Astrid Hofferson
Astrid Hofferson is a brave and skilled Viking warrior and dragon rider from the "How to Train Your Dragon" franchise, known as Hiccup's close friend and eventual love interest.
- 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: Marian Bering Triple: [Jolly Fellows, starring, Marian Bering]
Generated description
Marian Bering was an actress known for her role in the Soviet musical comedy film "Jolly Fellows."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Marian Bering Target entity description: Marian Bering was an actress known for her role in the Soviet musical comedy film "Jolly Fellows."
-
A.
Kathleen Bering
Kathleen Bering was the wife of silent film and stage actor Creighton Hale.
-
B.
Marianne Stenshagen
Marianne Stenshagen is a Norwegian speed skater who has competed at the international level representing Norway.
-
C.
Alison Arngrim
Alison Arngrim is an American actress and author best known for her iconic portrayal of the scheming Nellie Oleson on the classic television series "Little House on the Prairie."
-
D.
Margaret Halstan
Margaret Halstan was an English stage and film actress active in the late 19th and early 20th centuries, known for her refined character roles.
-
E.
Astrid Hofferson
Astrid Hofferson is a brave and skilled Viking warrior and dragon rider from the "How to Train Your Dragon" franchise, known as Hiccup's close friend and eventual love interest.
- 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_69e0c47b4e8c81908c8076eaa4c8e4f2 |
completed | April 16, 2026, 11:14 a.m. |
| NER | Named-entity recognition | batch_69f121d2d63c819090e115708aa4dbf8 |
completed | April 28, 2026, 9:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a5a06eb68819081aec85fc75ded17 |
completed | May 18, 2026, 12:15 a.m. |
| NEDg | Description generation | batch_6a0a5bd76d5c81909c64b14eeba5040d |
completed | May 18, 2026, 12:22 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a5c974d4c8190b3fe0e1c7354626a |
completed | May 18, 2026, 12:25 a.m. |
Created at: April 16, 2026, 7:21 p.m.