Triple
T18738270
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Amber Atkins |
E458222
|
entity |
| Predicate | friend |
P8712
|
FINISHED |
| Object |
Lisa Swenson
Lisa Swenson is a character from the dark comedy film "Drop Dead Gorgeous," known as one of Amber Atkins' close friends in their small-town beauty pageant world.
|
E1448444
|
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: Lisa Swenson | Statement: [Amber Atkins, friend, Lisa Swenson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Lisa Swenson Context triple: [Amber Atkins, friend, Lisa Swenson]
-
A.
Lisa Blount
Lisa Blount was an American actress and producer best known for her acclaimed supporting role in the film "An Officer and a Gentleman."
-
B.
Lisa Greer
Lisa Greer is a notable individual recognized for her contributions and public profile associated with the surname Greer.
-
C.
Karen Nelson
Karen Nelson is a central character in the 2018 horror film "Halloween," portrayed as Laurie Strode’s estranged daughter who must confront the legacy of Michael Myers.
-
D.
Lynn Baggett
Lynn Baggett was an American film actress of the 1940s and early 1950s, known for supporting roles in crime dramas and film noirs.
-
E.
Lyn Peters
Lyn Peters was a British-born actress and model who appeared in American television series and films during the 1960s and 1970s.
- 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: Lisa Swenson Triple: [Amber Atkins, friend, Lisa Swenson]
Generated description
Lisa Swenson is a character from the dark comedy film "Drop Dead Gorgeous," known as one of Amber Atkins' close friends in their small-town beauty pageant world.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Lisa Swenson Target entity description: Lisa Swenson is a character from the dark comedy film "Drop Dead Gorgeous," known as one of Amber Atkins' close friends in their small-town beauty pageant world.
-
A.
Lisa Blount
Lisa Blount was an American actress and producer best known for her acclaimed supporting role in the film "An Officer and a Gentleman."
-
B.
Lisa Greer
Lisa Greer is a notable individual recognized for her contributions and public profile associated with the surname Greer.
-
C.
Karen Nelson
Karen Nelson is a central character in the 2018 horror film "Halloween," portrayed as Laurie Strode’s estranged daughter who must confront the legacy of Michael Myers.
-
D.
Lynn Baggett
Lynn Baggett was an American film actress of the 1940s and early 1950s, known for supporting roles in crime dramas and film noirs.
-
E.
Lyn Peters
Lyn Peters was a British-born actress and model who appeared in American television series and films during the 1960s and 1970s.
- 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_69d8d394dc308190b6725073f5db324c |
completed | April 10, 2026, 10:40 a.m. |
| NER | Named-entity recognition | batch_69e5768b80ac8190bc05628d64f86fc9 |
completed | April 20, 2026, 12:42 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08e81e54d4819099def0167ac64e26 |
completed | May 16, 2026, 9:56 p.m. |
| NEDg | Description generation | batch_6a08e8fc1d6c819083f06debaa3bec24 |
completed | May 16, 2026, 10 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a08e98a594c8190b3a2d9ae7e3af4f7 |
completed | May 16, 2026, 10:02 p.m. |
Created at: April 10, 2026, 11:51 a.m.