Triple
T341939
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Paul McCartney |
E6854
|
entity |
| Predicate | memberOf |
P10
|
FINISHED |
| Object |
Wings
Wings was a British-American rock band formed by Paul McCartney after The Beatles, known for hits like "Band on the Run" and "Live and Let Die."
|
E43654
|
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: Wings | Statement: [Paul McCartney, memberOf, Wings]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Wings Context triple: [Paul McCartney, memberOf, Wings]
-
A.
Playland Park
Playland Park is a historic amusement park and beachside recreation area located along the Long Island Sound in Rye, Westchester County, New York.
-
B.
Honeycomb
"Honeycomb" is a popular 1957 pop song recorded by American singer Jimmie Rodgers that became one of his signature hits.
-
C.
Big Blue
Big Blue is the widely used nickname for the New York Giants, a professional American football team in the NFL.
-
D.
The Concert
The Concert is an unfinished and now missing painting by Dutch Golden Age master Johannes Vermeer, depicting an intimate scene of three figures making music in a domestic interior.
-
E.
Stardust
"Stardust" is a classic popular song, widely regarded as a jazz and American Songbook standard, famously interpreted by Louis Armstrong and many other artists.
- 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: Wings Triple: [Paul McCartney, memberOf, Wings]
Generated description
Wings was a British-American rock band formed by Paul McCartney after The Beatles, known for hits like "Band on the Run" and "Live and Let Die."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Wings Target entity description: Wings was a British-American rock band formed by Paul McCartney after The Beatles, known for hits like "Band on the Run" and "Live and Let Die."
-
A.
Playland Park
Playland Park is a historic amusement park and beachside recreation area located along the Long Island Sound in Rye, Westchester County, New York.
-
B.
Honeycomb
"Honeycomb" is a popular 1957 pop song recorded by American singer Jimmie Rodgers that became one of his signature hits.
-
C.
Big Blue
Big Blue is the widely used nickname for the New York Giants, a professional American football team in the NFL.
-
D.
The Concert
The Concert is an unfinished and now missing painting by Dutch Golden Age master Johannes Vermeer, depicting an intimate scene of three figures making music in a domestic interior.
-
E.
Stardust
"Stardust" is a classic popular song, widely regarded as a jazz and American Songbook standard, famously interpreted by Louis Armstrong and many other artists.
- 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_69a2e7951ba08190960e90823b5078f3 |
completed | Feb. 28, 2026, 1:03 p.m. |
| NER | Named-entity recognition | batch_69a2eafef8c88190a5932eb2c6ac4a5d |
completed | Feb. 28, 2026, 1:17 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a3d4e883ac81909f2acb66b7bfa540 |
completed | March 1, 2026, 5:55 a.m. |
| NEDg | Description generation | batch_69a3d56bead08190aefe0a5c6fef843e |
completed | March 1, 2026, 5:58 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69a3d62b40148190819686eda8669d6d |
completed | March 1, 2026, 6:01 a.m. |
Created at: Feb. 28, 2026, 1:08 p.m.