Triple
T5045369
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | T.I. |
E113648
|
entity |
| Predicate | notableWork |
P4
|
FINISHED |
| Object |
Paperwork
"Paperwork" is the debut studio album by American rapper T.I., showcasing his Southern hip hop style and lyrical themes of street life and success.
|
E489257
|
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: Paperwork | Statement: [T.I., notableWork, Paperwork]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Paperwork Context triple: [T.I., notableWork, Paperwork]
-
A.
The Paper
The Paper is a 1994 American comedy-drama film directed by Ron Howard that follows the hectic, deadline-driven day at a New York City tabloid newspaper.
-
B.
Mr. Papers
Mr. Papers is a rapper best known for his on-and-off romantic relationship with hip-hop icon Lil' Kim.
-
C.
Paper'd Up
"Paper'd Up" is a track by Snoop Dogg from his 2002 album "Paid tha Cost to Be da Boss," showcasing his West Coast hip-hop style and laid-back flow.
-
D.
Papel
Papel is an indigenous language of Guinea-Bissau spoken primarily by the Papel people in the coastal regions around Bissau.
-
E.
Makatib
Makatib is a collection of letters by the Persian Sufi poet Rumi, offering spiritual guidance, personal counsel, and insights into his mystical thought and relationships.
- 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: Paperwork Triple: [T.I., notableWork, Paperwork]
Generated description
"Paperwork" is the debut studio album by American rapper T.I., showcasing his Southern hip hop style and lyrical themes of street life and success.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Paperwork Target entity description: "Paperwork" is the debut studio album by American rapper T.I., showcasing his Southern hip hop style and lyrical themes of street life and success.
-
A.
The Paper
The Paper is a 1994 American comedy-drama film directed by Ron Howard that follows the hectic, deadline-driven day at a New York City tabloid newspaper.
-
B.
Mr. Papers
Mr. Papers is a rapper best known for his on-and-off romantic relationship with hip-hop icon Lil' Kim.
-
C.
Paper'd Up
"Paper'd Up" is a track by Snoop Dogg from his 2002 album "Paid tha Cost to Be da Boss," showcasing his West Coast hip-hop style and laid-back flow.
-
D.
Papel
Papel is an indigenous language of Guinea-Bissau spoken primarily by the Papel people in the coastal regions around Bissau.
-
E.
Makatib
Makatib is a collection of letters by the Persian Sufi poet Rumi, offering spiritual guidance, personal counsel, and insights into his mystical thought and relationships.
- 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_69bd44391fc48190a311ce9c826c209b |
completed | March 20, 2026, 12:57 p.m. |
| NER | Named-entity recognition | batch_69bd73fd81788190b7799f519277119a |
completed | March 20, 2026, 4:21 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be9c8ad6408190bf4408af7b095a12 |
completed | March 21, 2026, 1:26 p.m. |
| NEDg | Description generation | batch_69be9f91ae7081908a00cf92b5461c75 |
completed | March 21, 2026, 1:39 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69bea0155838819082b4b04e79641d65 |
completed | March 21, 2026, 1:41 p.m. |
Created at: March 20, 2026, 1:37 p.m.