Triple
T23226711
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Stooge |
E581034
|
entity |
| Predicate | hasMainCharacter |
P1183
|
FINISHED |
| Object |
Bill Miller
Bill Miller is the central character of the film "The Stooge," portrayed by comedian Jerry Lewis.
|
E1578018
|
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: Bill Miller | Statement: [The Stooge, hasMainCharacter, Bill Miller]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Bill Miller Context triple: [The Stooge, hasMainCharacter, Bill Miller]
-
A.
Bill Miller
Bill Miller is a veteran Major League Baseball umpire who has officiated numerous high-profile games, including multiple World Series.
-
B.
Bill Miller
Bill Miller is a film producer best known for his work on the Academy Award–winning animated feature "Happy Feet."
-
C.
Bill Miller
Bill Miller is the blue-collar, sarcastic yet well-meaning father and central character in the American sitcom "Still Standing."
-
D.
William F. Miller
William F. Miller was a prominent American physicist, academic leader, and technology executive known for his contributions to innovation management and university–industry collaboration.
-
E.
Bill Gross
Bill Gross is an American entrepreneur and investor best known for founding numerous technology companies and the startup incubator Idealab.
- 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: Bill Miller Triple: [The Stooge, hasMainCharacter, Bill Miller]
Generated description
Bill Miller is the central character of the film "The Stooge," portrayed by comedian Jerry Lewis.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Bill Miller Target entity description: Bill Miller is the central character of the film "The Stooge," portrayed by comedian Jerry Lewis.
-
A.
Bill Miller
Bill Miller is a veteran Major League Baseball umpire who has officiated numerous high-profile games, including multiple World Series.
-
B.
Bill Miller
Bill Miller is a film producer best known for his work on the Academy Award–winning animated feature "Happy Feet."
-
C.
Bill Miller
Bill Miller is the blue-collar, sarcastic yet well-meaning father and central character in the American sitcom "Still Standing."
-
D.
William F. Miller
William F. Miller was a prominent American physicist, academic leader, and technology executive known for his contributions to innovation management and university–industry collaboration.
-
E.
Bill Gross
Bill Gross is an American investor and fund manager widely known as the "Bond King" for co-founding and leading PIMCO to prominence in fixed-income investing.
- 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_69e246043c48819089bae72c9a9c306c |
completed | April 17, 2026, 2:39 p.m. |
| NER | Named-entity recognition | batch_69f1922f5b4081908145d66ea7534493 |
completed | April 29, 2026, 5:07 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c3f53f60c8190b0f7d66a360b9897 |
completed | May 19, 2026, 10:45 a.m. |
| NEDg | Description generation | batch_6a0c4075bc508190ae0dc8b61c24faa0 |
completed | May 19, 2026, 10:50 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c411702a48190ba2964ba221394d1 |
completed | May 19, 2026, 10:53 a.m. |
Created at: April 17, 2026, 4:09 p.m.