Triple
T2350765
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 28 Days Later |
E47441
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Megan Burns
Megan Burns is a British actress best known for her role as Hannah in the post-apocalyptic horror film "28 Days Later."
|
E364589
|
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: Megan Burns | Statement: [28 Days Later, starring, Megan Burns]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Megan Burns Context triple: [28 Days Later, starring, Megan Burns]
-
A.
Megan Foster
Megan Foster is an American local government leader serving as the mayor of Coralville, Iowa.
-
B.
Megan McArthur
Megan McArthur is a NASA astronaut and oceanographer best known for her role as a mission specialist on Space Shuttle missions, including the final Hubble Space Telescope servicing flight.
-
C.
Megan Davis
Megan Davis is an Australian constitutional lawyer and Indigenous rights advocate renowned for her leadership in advancing Aboriginal and Torres Strait Islander peoples’ rights and constitutional recognition.
-
D.
Megan Holley
Megan Holley is an American screenwriter best known for writing the indie dramedy film "Sunshine Cleaning."
-
E.
Megan Walsh
Megan Walsh is the teenage government-trained assassin who goes undercover as a high school student in the action-comedy film "Barely Lethal."
- 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: Megan Burns Triple: [28 Days Later, starring, Megan Burns]
Generated description
Megan Burns is a British actress best known for her role as Hannah in the post-apocalyptic horror film "28 Days Later."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Megan Burns Target entity description: Megan Burns is a British actress best known for her role as Hannah in the post-apocalyptic horror film "28 Days Later."
-
A.
Megan Foster
Megan Foster is an American local government leader serving as the mayor of Coralville, Iowa.
-
B.
Megan McArthur
Megan McArthur is a NASA astronaut and oceanographer best known for her role as a mission specialist on Space Shuttle missions, including the final Hubble Space Telescope servicing flight.
-
C.
Megan Davis
Megan Davis is an Australian constitutional lawyer and Indigenous rights advocate renowned for her leadership in advancing Aboriginal and Torres Strait Islander peoples’ rights and constitutional recognition.
-
D.
Megan Holley
Megan Holley is an American screenwriter best known for writing the indie dramedy film "Sunshine Cleaning."
-
E.
Megan Walsh
Megan Walsh is the teenage government-trained assassin who goes undercover as a high school student in the action-comedy film "Barely Lethal."
- 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_69a88a1b678c8190bce986922ba60ce0 |
completed | March 4, 2026, 7:38 p.m. |
| NER | Named-entity recognition | batch_69abc6cfffc88190b49433f52581420e |
completed | March 7, 2026, 6:33 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b37e38ff2881909490b7b20deb149b |
completed | March 13, 2026, 3:02 a.m. |
| NEDg | Description generation | batch_69b37f44417481908dc7e04dc112d900 |
completed | March 13, 2026, 3:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b37fa6b5c08190bb598c77c526df13 |
completed | March 13, 2026, 3:08 a.m. |
Created at: March 4, 2026, 7:54 p.m.