Triple
T3022901
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Yeller |
E82505
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
William Tunberg
William Tunberg was an American screenwriter best known for adapting the classic 1957 Disney film "Old Yeller."
|
E324201
|
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: William Tunberg | Statement: [Old Yeller, screenwriter, William Tunberg]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: William Tunberg Context triple: [Old Yeller, screenwriter, William Tunberg]
-
A.
Carl F. Wallin
Carl F. Wallin was an early 20th-century American businessman best known as the co-founder of the Nordstrom retail company.
-
B.
Carl F. Wallin
Carl F. Wallin was a Swedish businessman active in early 20th-century trade and industry, known for his commercial partnerships such as with Johan Nordström.
-
C.
Sten Carl Bielke
Sten Carl Bielke was an 18th-century Swedish statesman and scientist who played a key role in advancing scientific institutions in Sweden.
-
D.
William Wendt
William Wendt was a prominent American landscape painter celebrated as a leading figure of the California Impressionist movement.
-
E.
Frederic Knudtson
Frederic Knudtson was an American film editor known for his work on numerous Hollywood productions in the mid-20th century.
- 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: William Tunberg Triple: [Old Yeller, screenwriter, William Tunberg]
Generated description
William Tunberg was an American screenwriter best known for adapting the classic 1957 Disney film "Old Yeller."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: William Tunberg Target entity description: William Tunberg was an American screenwriter best known for adapting the classic 1957 Disney film "Old Yeller."
-
A.
Carl F. Wallin
Carl F. Wallin was an early 20th-century American businessman best known as the co-founder of the Nordstrom retail company.
-
B.
Carl F. Wallin
Carl F. Wallin was a Swedish businessman active in early 20th-century trade and industry, known for his commercial partnerships such as with Johan Nordström.
-
C.
Sten Carl Bielke
Sten Carl Bielke was an 18th-century Swedish statesman and scientist who played a key role in advancing scientific institutions in Sweden.
-
D.
William Wendt
William Wendt was a prominent American landscape painter celebrated as a leading figure of the California Impressionist movement.
-
E.
Frederic Knudtson
Frederic Knudtson was an American film editor known for his work on numerous Hollywood productions in the mid-20th century.
- 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_69ad8b1fb34081908c1b873e2b7273e1 |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad9a963034819093d96566e9b0cea9 |
completed | March 8, 2026, 3:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b1f86995c88190bdf3af6f96f7a195 |
completed | March 11, 2026, 11:19 p.m. |
| NEDg | Description generation | batch_69b1f8d3ff288190bd79bfc99d06c3ca |
completed | March 11, 2026, 11:20 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b1f94b3e3c8190b8ce0531a7c54902 |
completed | March 11, 2026, 11:22 p.m. |
Created at: March 8, 2026, 3 p.m.