Triple
T17435875
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Scar |
E423999
|
entity |
| Predicate | kills |
P19780
|
FINISHED |
| Object |
Brad Jorgensen
Brad Jorgensen is a fictional character known primarily as a victim of the villainous lion Scar in The Lion King universe.
|
E1268706
|
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: Brad Jorgensen | Statement: [Scar, kills, Brad Jorgensen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Brad Jorgensen Context triple: [Scar, kills, Brad Jorgensen]
-
A.
Wink Jorgensen
Wink Jorgensen is an architect best known for designing the Thomas & Mack Center, a major multi-purpose arena in Las Vegas, Nevada.
-
B.
Brian Swardstrom
Brian Swardstrom is a prominent American talent agent and partner at United Talent Agency, known for representing acclaimed actors and filmmakers.
-
C.
Johnny Jorgensen
Johnny Jorgensen was a professional basketball player best known for his time in the early Basketball Association of America, including a stint with the Cleveland Rebels.
-
D.
Brian Skrudland
Brian Skrudland is a former Canadian NHL center known for his leadership, defensive play, and role as the first captain of the Florida Panthers.
-
E.
Erik Jendresen
Erik Jendresen is an American writer and producer best known for his work on the acclaimed World War II miniseries "Band of Brothers."
- 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: Brad Jorgensen Triple: [Scar, kills, Brad Jorgensen]
Generated description
Brad Jorgensen is a fictional character known primarily as a victim of the villainous lion Scar in The Lion King universe.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Brad Jorgensen Target entity description: Brad Jorgensen is a fictional character known primarily as a victim of the villainous lion Scar in The Lion King universe.
-
A.
Wink Jorgensen
Wink Jorgensen is an architect best known for designing the Thomas & Mack Center, a major multi-purpose arena in Las Vegas, Nevada.
-
B.
Brian Swardstrom
Brian Swardstrom is a prominent American talent agent and partner at United Talent Agency, known for representing acclaimed actors and filmmakers.
-
C.
Johnny Jorgensen
Johnny Jorgensen was a professional basketball player best known for his time in the early Basketball Association of America, including a stint with the Cleveland Rebels.
-
D.
Brian Skrudland
Brian Skrudland is a former Canadian NHL center known for his leadership, defensive play, and role as the first captain of the Florida Panthers.
-
E.
Erik Jendresen
Erik Jendresen is an American writer and producer best known for his work on the acclaimed World War II miniseries "Band of Brothers."
- 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_69d889d88b6081908bada047f5b3ba51 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e4490426008190b474ed76aca5d6f3 |
completed | April 19, 2026, 3:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01aff0b26c8190a6e65451e52199bb |
completed | May 11, 2026, 10:31 a.m. |
| NEDg | Description generation | batch_6a01b12b5df4819089fd89fd25338533 |
completed | May 11, 2026, 10:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01b17486c08190aa47953e74c62e84 |
completed | May 11, 2026, 10:37 a.m. |
Created at: April 10, 2026, 5:46 a.m.