Triple
T4761325
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Krampus (2015 film) |
E105703
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Tom Engel
Tom Engel is the young boy protagonist in the 2015 horror-comedy film "Krampus," whose loss of Christmas spirit triggers the arrival of the folkloric monster.
|
E466921
|
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: Tom Engel | Statement: [Krampus (2015 film), mainCharacter, Tom Engel]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Engel Context triple: [Krampus (2015 film), mainCharacter, Tom Engel]
-
A.
John Eisendrath
John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
-
B.
Hal Bidlack
Hal Bidlack is an American political science professor, retired U.S. Air Force officer, and public speaker known for his work in skepticism and secular humanism.
-
C.
Marc Ewing
Marc Ewing is an American software engineer and entrepreneur best known as a co-founder of the open-source software company Red Hat.
-
D.
Tom Leppert
Tom Leppert is an American businessman and politician who served as the mayor of Dallas, Texas, and later ran for the U.S. Senate.
-
E.
Bob Tzudiker
Bob Tzudiker is an American screenwriter best known for co-writing Disney animated films such as "Tarzan" and "The Lion King."
- 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: Tom Engel Triple: [Krampus (2015 film), mainCharacter, Tom Engel]
Generated description
Tom Engel is the young boy protagonist in the 2015 horror-comedy film "Krampus," whose loss of Christmas spirit triggers the arrival of the folkloric monster.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tom Engel Target entity description: Tom Engel is the young boy protagonist in the 2015 horror-comedy film "Krampus," whose loss of Christmas spirit triggers the arrival of the folkloric monster.
-
A.
John Eisendrath
John Eisendrath is a television writer and producer best known for his work on series such as "The Blacklist" and "Alias."
-
B.
Hal Bidlack
Hal Bidlack is an American political science professor, retired U.S. Air Force officer, and public speaker known for his work in skepticism and secular humanism.
-
C.
Marc Ewing
Marc Ewing is an American software engineer and entrepreneur best known as a co-founder of the open-source software company Red Hat.
-
D.
Tom Leppert
Tom Leppert is an American businessman and politician who served as the mayor of Dallas, Texas, and later ran for the U.S. Senate.
-
E.
Bob Tzudiker
Bob Tzudiker is an American screenwriter best known for co-writing Disney animated films such as "Tarzan" and "The Lion King."
- 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_69bd43f14cac819081c7c69803648211 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd650eefe08190b99f9f01b121dbfd |
completed | March 20, 2026, 3:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be3a7c72c48190a562d6261e323b4b |
completed | March 21, 2026, 6:28 a.m. |
| NEDg | Description generation | batch_69be3c81c7b4819099d2627e7aa1611c |
completed | March 21, 2026, 6:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be3d0aa1d48190a2af91d251cb5561 |
completed | March 21, 2026, 6:39 a.m. |
Created at: March 20, 2026, 1:20 p.m.