Triple
T15905945
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rachael Taylor |
E385714
|
entity |
| Predicate | playedCharacter |
P1507
|
FINISHED |
| Object |
Maggie Madsen
Maggie Madsen is a brilliant Australian signals analyst and hacker character in the 2007 film "Transformers."
|
E1193872
|
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: Maggie Madsen | Statement: [Rachael Taylor, playedCharacter, Maggie Madsen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maggie Madsen Context triple: [Rachael Taylor, playedCharacter, Maggie Madsen]
-
A.
Molly O'Neil
Molly O'Neil is the daughter of American actress and comedian Teri Garr.
-
B.
Taryn Van Dyke
Taryn Van Dyke is a member of the Van Dyke family, known for its multi-generational involvement in American film and television.
-
C.
Megan Fairchild
Megan Fairchild is an acclaimed American ballet dancer and principal with New York City Ballet, known for her virtuosity in both classical and contemporary roles.
-
D.
Sara Paxton
Sara Paxton is an American actress and singer known for her roles in films such as "Aquamarine," "The Last House on the Left," and various television series.
-
E.
Melora Hardin
Melora Hardin is an American actress and singer best known for her roles in television series such as "The Office" and "Monk," as well as numerous film and stage performances.
- 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: Maggie Madsen Triple: [Rachael Taylor, playedCharacter, Maggie Madsen]
Generated description
Maggie Madsen is a brilliant Australian signals analyst and hacker character in the 2007 film "Transformers."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Maggie Madsen Target entity description: Maggie Madsen is a brilliant Australian signals analyst and hacker character in the 2007 film "Transformers."
-
A.
Molly O'Neil
Molly O'Neil is the daughter of American actress and comedian Teri Garr.
-
B.
Taryn Van Dyke
Taryn Van Dyke is a member of the Van Dyke family, known for its multi-generational involvement in American film and television.
-
C.
Megan Fairchild
Megan Fairchild is an acclaimed American ballet dancer and principal with New York City Ballet, known for her virtuosity in both classical and contemporary roles.
-
D.
Sara Paxton
Sara Paxton is an American actress and singer known for her roles in films such as "Aquamarine," "The Last House on the Left," and various television series.
-
E.
Melora Hardin
Melora Hardin is an American actress and singer best known for her roles in television series such as "The Office" and "Monk," as well as numerous film and stage performances.
- 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_69d86da686e4819097cbf3b1fc2d881d |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e1565956588190ba4726a2879b677d |
completed | April 16, 2026, 9:36 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ffeb82a29081909ef0e2685d0705c3 |
completed | May 10, 2026, 2:20 a.m. |
| NEDg | Description generation | batch_69ffec4898088190bed531e33418c7e5 |
completed | May 10, 2026, 2:24 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69ffecce96508190a53f100e3207ebac |
completed | May 10, 2026, 2:26 a.m. |
Created at: April 10, 2026, 4:52 a.m.