Triple
T28673811
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Keyhouse |
E725804
|
entity |
| Predicate | visualDesigner |
P29429
|
FINISHED |
| Object |
Gabriel Rodríguez
Gabriel Rodríguez is a Chilean comic book artist best known for his detailed, atmospheric artwork on the horror-fantasy series "Locke & Key."
|
E194796
|
NE FINISHED |
How this triple was built (3 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: Gabriel Rodríguez | Statement: [Keyhouse, visualDesigner, Gabriel Rodríguez]
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: Gabriel Rodríguez Triple: [Keyhouse, visualDesigner, Gabriel Rodríguez]
Generated description
Gabriel Rodríguez is a Chilean comic book artist best known for his detailed, atmospheric artwork on the horror-fantasy series "Locke & Key."
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: visualDesigner Context triple: [Keyhouse, visualDesigner, Gabriel Rodríguez]
-
A.
visualForm
Indicates the visual appearance, shape, or structural pattern that characterizes how something looks.
-
B.
visualElements
chosen
Indicates that one entity contains, uses, or is characterized by specific visual components or graphical features associated with another entity.
-
C.
designCenter
Indicates that an entity serves as the primary location or hub where another entity is designed or conceptually developed.
-
D.
propDesigner
Indicates that an entity serves as the designer or creator of a particular property, item, or artifact.
-
E.
designModel
Indicates that one entity creates, specifies, or defines the structure or behavior of another entity as a model or blueprint.
- F. None of above.
Provenance (6 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_69f01d85be388190b669a0e401e2f2c4 |
completed | April 28, 2026, 2:37 a.m. |
| NER | Named-entity recognition | batch_69f65a6c900881908f18b61273d7bf8d |
completed | May 2, 2026, 8:11 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a1ccf4257a881908c8dccda94822686 |
completed | June 1, 2026, 12:16 a.m. |
| NEDg | Description generation | batch_6a1cd020780c81908d33cd9d1676a762 |
completed | June 1, 2026, 12:19 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a24945efab88190a4ccb8a92331e469 |
completed | June 6, 2026, 9:42 p.m. |
| PD | Predicate disambiguation | batch_69f659ce58408190ba9e007b4810d4d0 |
completed | May 2, 2026, 8:08 p.m. |
Created at: April 28, 2026, 5:05 a.m.