Triple
T14691379
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Emily the Criminal |
E345042
|
entity |
| Predicate | producer |
P490
|
FINISHED |
| Object |
Drew Sykes
Drew Sykes is a film producer known for his work on the crime thriller "Emily the Criminal."
|
E1114951
|
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: Drew Sykes | Statement: [Emily the Criminal, producer, Drew Sykes]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Drew Sykes Context triple: [Emily the Criminal, producer, Drew Sykes]
-
A.
Drew Gordon
Drew Gordon was an American professional basketball player and standout collegiate forward known for his dominant rebounding and interior play, particularly at the University of New Mexico.
-
B.
Drew MacFarlane
Drew MacFarlane is a British musician best known as the guitarist and keyboardist for the indie rock band Glass Animals.
-
C.
Dylan Marshall
Dylan Marshall is a recurring character on the television series "Modern Family," known as Haley Dunphy’s on-and-off boyfriend who later becomes her husband.
-
D.
Drew Ferguson
Drew Ferguson is an American Republican politician and dentist serving as a U.S. Representative from Georgia.
-
E.
Matthew Dawson
Matthew Dawson was a prominent 19th-century British racehorse trainer renowned for preparing multiple classic-winning Thoroughbreds.
- 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: Drew Sykes Triple: [Emily the Criminal, producer, Drew Sykes]
Generated description
Drew Sykes is a film producer known for his work on the crime thriller "Emily the Criminal."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Drew Sykes Target entity description: Drew Sykes is a film producer known for his work on the crime thriller "Emily the Criminal."
-
A.
Drew Gordon
Drew Gordon was an American professional basketball player and standout collegiate forward known for his dominant rebounding and interior play, particularly at the University of New Mexico.
-
B.
Drew MacFarlane
Drew MacFarlane is a British musician best known as the guitarist and keyboardist for the indie rock band Glass Animals.
-
C.
Dylan Marshall
Dylan Marshall is a recurring character on the television series "Modern Family," known as Haley Dunphy’s on-and-off boyfriend who later becomes her husband.
-
D.
Drew Ferguson
Drew Ferguson is an American Republican politician and dentist serving as a U.S. Representative from Georgia.
-
E.
Matthew Dawson
Matthew Dawson was a prominent 19th-century British racehorse trainer renowned for preparing multiple classic-winning Thoroughbreds.
- 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_69d822e34b348190ada4d1cdb6c7c226 |
completed | April 9, 2026, 10:06 p.m. |
| NER | Named-entity recognition | batch_69deb585d46c81908d6964130914cec4 |
completed | April 14, 2026, 9:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fdf08274ac8190b5ba0752d36a690b |
completed | May 8, 2026, 2:17 p.m. |
| NEDg | Description generation | batch_69fdf21ff584819098d5bc66fd667edf |
completed | May 8, 2026, 2:24 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69fdf2980d188190a81474df8097aab7 |
completed | May 8, 2026, 2:26 p.m. |
Created at: April 10, 2026, 1:28 a.m.