Triple
T9721
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Legend |
E196
|
entity |
| Predicate | notableSong |
P4
|
FINISHED |
| Object |
Save Room
"Save Room" is a soulful R&B single by John Legend, known for its smooth melody and romantic lyrics.
|
E2156
|
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: Save Room | Statement: [John Legend, notableSong, Save Room]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Save Room Context triple: [John Legend, notableSong, Save Room]
-
A.
Blitz
The Blitz was the sustained German bombing campaign against the United Kingdom, particularly London, during 1940–1941 in World War II.
-
B.
The Palestra
The Palestra is a historic college basketball arena on the University of Pennsylvania campus in Philadelphia, renowned as one of the most storied and frequently used venues in the sport.
-
C.
Evolver
Evolver is a studio album by American singer-songwriter John Legend that blends R&B, soul, and pop influences.
-
D.
Terminal 8
Terminal 8 is a major passenger terminal at New York’s John F. Kennedy International Airport, serving as a primary hub for American Airlines and several international carriers.
-
E.
HUP
HUP is a major academic medical center in Philadelphia that serves as the flagship teaching hospital of the University of Pennsylvania's health system.
- 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: Save Room Triple: [John Legend, notableSong, Save Room]
Generated description
"Save Room" is a soulful R&B single by John Legend, known for its smooth melody and romantic lyrics.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Save Room Target entity description: "Save Room" is a soulful R&B single by John Legend, known for its smooth melody and romantic lyrics.
-
A.
Blitz
The Blitz was the sustained German bombing campaign against the United Kingdom, particularly London, during 1940–1941 in World War II.
-
B.
The Palestra
The Palestra is a historic college basketball arena on the University of Pennsylvania campus in Philadelphia, renowned as one of the most storied and frequently used venues in the sport.
-
C.
Blue Room
The Blue Room is an oval-shaped ceremonial reception room on the first floor of the White House, traditionally decorated in blue and used for formal gatherings and receiving guests.
-
D.
Evolver
Evolver is a studio album by American singer-songwriter John Legend that blends R&B, soul, and pop influences.
-
E.
Terminal 8
Terminal 8 is a major passenger terminal at New York’s John F. Kennedy International Airport, serving as a primary hub for American Airlines and several international carriers.
- 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_69a23bb612708190b09f25385e4b63d1 |
completed | Feb. 28, 2026, 12:49 a.m. |
| NER | Named-entity recognition | batch_69a2465b2cf881908bf61c461e04cf6a |
completed | Feb. 28, 2026, 1:35 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a248deaab88190952bad0998755baf |
completed | Feb. 28, 2026, 1:46 a.m. |
| NEDg | Description generation | batch_69a24cd6aa80819084770080b00c6e49 |
completed | Feb. 28, 2026, 2:03 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a24d8ad4dc8190a011b92da1c3ddde |
completed | Feb. 28, 2026, 2:06 a.m. |
Created at: Feb. 28, 2026, 12:54 a.m.