Triple
T20684984
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harry Earles |
E508389
|
entity |
| Predicate | sibling |
P363
|
FINISHED |
| Object |
Tiny Earles
Tiny Earles was a German-born American dwarf actor and circus performer known for his roles in early 20th-century films and sideshows.
|
E1445883
|
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: Tiny Earles | Statement: [Harry Earles, sibling, Tiny Earles]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tiny Earles Context triple: [Harry Earles, sibling, Tiny Earles]
-
A.
Tiny Wells
Tiny Wells is an actor known for appearing in the film "American Anthem."
-
B.
Todd Smallie
Todd Smallie is an American bassist best known for his long tenure with the Derek Trucks Band, where he contributed to their blend of blues, rock, jazz, and world music.
-
C.
Earle
Earle is the middle name of Gordon E. Moore, the co-founder of Intel and originator of Moore’s Law.
-
D.
Earle
Earle is a surname most notably associated with Eyvind Earle, the American artist and illustrator renowned for his distinctive background styling in Disney animated films.
-
E.
Little Leota
Little Leota is a smaller, ghostly bride-like character in Disney's Haunted Mansion attraction, known for her eerie farewell line to departing guests.
- 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: Tiny Earles Triple: [Harry Earles, sibling, Tiny Earles]
Generated description
Tiny Earles was a German-born American dwarf actor and circus performer known for his roles in early 20th-century films and sideshows.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tiny Earles Target entity description: Tiny Earles was a German-born American dwarf actor and circus performer known for his roles in early 20th-century films and sideshows.
-
A.
Tiny Wells
Tiny Wells is an actor known for appearing in the film "American Anthem."
-
B.
Todd Smallie
Todd Smallie is an American bassist best known for his long tenure with the Derek Trucks Band, where he contributed to their blend of blues, rock, jazz, and world music.
-
C.
Earle
Earle is the middle name of Gordon E. Moore, the co-founder of Intel and originator of Moore’s Law.
-
D.
Earle
Earle is a surname most notably associated with Eyvind Earle, the American artist and illustrator renowned for his distinctive background styling in Disney animated films.
-
E.
Little Leota
Little Leota is a smaller, ghostly bride-like character in Disney's Haunted Mansion attraction, known for her eerie farewell line to departing guests.
- 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_69e0b4c1ed408190b72dd26b1e33f8a1 |
completed | April 16, 2026, 10:06 a.m. |
| NER | Named-entity recognition | batch_69e6beabf72881909771b6c6a81276d6 |
completed | April 21, 2026, 12:02 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08d7de62a8819088a43b43dc7873ec |
completed | May 16, 2026, 8:47 p.m. |
| NEDg | Description generation | batch_6a08da13f584819090d491c821e12f29 |
completed | May 16, 2026, 8:56 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08daae48048190a71c46941d2a5d36 |
completed | May 16, 2026, 8:59 p.m. |
Created at: April 16, 2026, 11:45 a.m.