Triple
T17909719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rigby |
E447788
|
entity |
| Predicate | livesIn |
P40
|
FINISHED |
| Object |
The Park house
The Park house is Rigby’s shared residence in the animated series "Regular Show," serving as a central setting for many of the show's events and character interactions.
|
E1295249
|
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: The Park house | Statement: [Rigby, livesIn, The Park house]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: The Park house Context triple: [Rigby, livesIn, The Park house]
-
A.
The Parkside Lodge
The Parkside Lodge is a historic event and community facility located within Delaware Park in Buffalo, New York.
-
B.
Newton Park House
Newton Park House is a historic country house that serves as a central landmark and facility within the Newton Park campus.
-
C.
Lee House
Lee House is one of the historic townhouses that together form the Blair House complex, the official guest residence for visiting dignitaries in Washington, D.C.
-
D.
Arbor House
Arbor House was an American publishing company known for releasing notable works of crime and mystery fiction in the late 20th century.
-
E.
Pat House
Pat House is a technology executive best known as a co-founder of Siebel Systems, a pioneering customer relationship management (CRM) software company.
- 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: The Park house Triple: [Rigby, livesIn, The Park house]
Generated description
The Park house is Rigby’s shared residence in the animated series "Regular Show," serving as a central setting for many of the show's events and character interactions.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: The Park house Target entity description: The Park house is Rigby’s shared residence in the animated series "Regular Show," serving as a central setting for many of the show's events and character interactions.
-
A.
The Parkside Lodge
The Parkside Lodge is a historic event and community facility located within Delaware Park in Buffalo, New York.
-
B.
Newton Park House
Newton Park House is a historic country house that serves as a central landmark and facility within the Newton Park campus.
-
C.
Lee House
Lee House is one of the historic townhouses that together form the Blair House complex, the official guest residence for visiting dignitaries in Washington, D.C.
-
D.
Arbor House
Arbor House was an American publishing company known for releasing notable works of crime and mystery fiction in the late 20th century.
-
E.
Pat House
Pat House is a technology executive best known as a co-founder of Siebel Systems, a pioneering customer relationship management (CRM) software company.
- 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_69d8b9f6d394819082a6d69fd1e23d2f |
completed | April 10, 2026, 8:51 a.m. |
| NER | Named-entity recognition | batch_69e49e9f4f888190840c8b55672becf8 |
completed | April 19, 2026, 9:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a031b2e0c5481908443e13839a0415d |
completed | May 12, 2026, 12:21 p.m. |
| NEDg | Description generation | batch_6a031bc800d081908493949af23dd360 |
completed | May 12, 2026, 12:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_6a031d4bf2dc8190b69eb8f8050b9955 |
completed | May 12, 2026, 12:30 p.m. |
Created at: April 10, 2026, 10:19 a.m.