Triple
T8135246
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thomas "Babe" Levy |
E189953
|
entity |
| Predicate | nickname |
P55
|
FINISHED |
| Object |
Babe
Babe is the nickname of Thomas "Babe" Levy, the fictional graduate student and marathon runner portrayed by Dustin Hoffman in the 1976 thriller film "Marathon Man."
|
E714175
|
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: Babe | Statement: [Thomas "Babe" Levy, nickname, Babe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Babe Context triple: [Thomas "Babe" Levy, nickname, Babe]
-
A.
Babe
Babe is the famous nickname of George Herman "Babe" Ruth, the legendary American baseball player widely regarded as one of the greatest hitters in the sport's history.
-
B.
Babe
"Babe" is a 1990s pop song by the British boy band Take That, known as one of their early hit ballads.
-
C.
Babe
Babe is a critically acclaimed 1995 family film that blends live-action and animatronics to tell the story of a pig who aspires to be a sheepdog.
-
D.
Babe
"Babe" is a novel by American author Marianne Wiggins, known for its inventive narrative voice and exploration of complex personal relationships.
-
E.
Babe
Babe is the nickname of Babe Phelps, an American Major League Baseball catcher active in the 1930s and early 1940s.
- 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: Babe Triple: [Thomas "Babe" Levy, nickname, Babe]
Generated description
Babe is the nickname of Thomas "Babe" Levy, the fictional graduate student and marathon runner portrayed by Dustin Hoffman in the 1976 thriller film "Marathon Man."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Babe Target entity description: Babe is the nickname of Thomas "Babe" Levy, the fictional graduate student and marathon runner portrayed by Dustin Hoffman in the 1976 thriller film "Marathon Man."
-
A.
Babe
Babe is the famous nickname of George Herman "Babe" Ruth, the legendary American baseball player widely regarded as one of the greatest hitters in the sport's history.
-
B.
Babe
Babe is a critically acclaimed 1995 family film that blends live-action and animatronics to tell the story of a pig who aspires to be a sheepdog.
-
C.
Babe
"Babe" is a novel by American author Marianne Wiggins, known for its inventive narrative voice and exploration of complex personal relationships.
-
D.
Babe
Babe is the nickname of Babe Phelps, an American Major League Baseball catcher active in the 1930s and early 1940s.
-
E.
Babe
"Babe" is a 1990s pop song by the British boy band Take That, known as one of their early hit ballads.
- 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_69ca82bcb4848190a9a9d036ad768642 |
completed | March 30, 2026, 2:03 p.m. |
| NER | Named-entity recognition | batch_69cb43fff6e0819086c95b571272b50c |
completed | March 31, 2026, 3:48 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cc949065248190b67ba7aa2688903e |
completed | April 1, 2026, 3:44 a.m. |
| NEDg | Description generation | batch_69cc95c180188190a2d541e8ea9a4c57 |
completed | April 1, 2026, 3:49 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69cc970cf55c8190abf432ac68d6bbc3 |
completed | April 1, 2026, 3:54 a.m. |
Created at: March 30, 2026, 5:35 p.m.