Triple
T3360659
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dancing on the Ceiling |
E70712
|
entity |
| Predicate | writer |
P1360
|
FINISHED |
| Object |
Michael Frenchik
Michael Frenchik is a songwriter best known for his work on the hit track "Dancing on the Ceiling."
|
E351991
|
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: Michael Frenchik | Statement: [Dancing on the Ceiling, writer, Michael Frenchik]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Michael Frenchik Context triple: [Dancing on the Ceiling, writer, Michael Frenchik]
-
A.
Jonathan Pytko
Jonathan Pytko is a cinematographer best known for his work on the Pixar animated film "Turning Red."
-
B.
David Franzoni
David Franzoni is an American screenwriter and film producer best known for his work on the Academy Award–winning historical epic "Gladiator."
-
C.
Jason Fuchs
Jason Fuchs is an American screenwriter and actor best known for writing major studio films such as Wonder Woman (2017) and Pan (2015).
-
D.
Ian La Frenais
Ian La Frenais is a British screenwriter best known for co-creating classic TV comedies such as "Porridge" and "Auf Wiedersehen, Pet," and for his long-time writing partnership with Dick Clement.
-
E.
Michael Filerman
Michael Filerman was an American television producer best known for developing and producing popular prime-time soap operas during the 1970s and 1980s.
- 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: Michael Frenchik Triple: [Dancing on the Ceiling, writer, Michael Frenchik]
Generated description
Michael Frenchik is a songwriter best known for his work on the hit track "Dancing on the Ceiling."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Michael Frenchik Target entity description: Michael Frenchik is a songwriter best known for his work on the hit track "Dancing on the Ceiling."
-
A.
Jonathan Pytko
Jonathan Pytko is a cinematographer best known for his work on the Pixar animated film "Turning Red."
-
B.
David Franzoni
David Franzoni is an American screenwriter and film producer best known for his work on the Academy Award–winning historical epic "Gladiator."
-
C.
Jason Fuchs
Jason Fuchs is an American screenwriter and actor best known for writing major studio films such as Wonder Woman (2017) and Pan (2015).
-
D.
Ian La Frenais
Ian La Frenais is a British screenwriter best known for co-creating classic TV comedies such as "Porridge" and "Auf Wiedersehen, Pet," and for his long-time writing partnership with Dick Clement.
-
E.
Michael Filerman
Michael Filerman was an American television producer best known for developing and producing popular prime-time soap operas during the 1970s and 1980s.
- 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_69ad85a660c48190998489309a3b4869 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb267ec1081909a4e3e227d5bad01 |
completed | March 8, 2026, 5:31 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b32541ed808190aa7be7d0b7606426 |
completed | March 12, 2026, 8:42 p.m. |
| NEDg | Description generation | batch_69b3293d4b688190be472a5a3b56293b |
completed | March 12, 2026, 8:59 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b32a49fed0819094ffd1e93a3757d0 |
completed | March 12, 2026, 9:04 p.m. |
Created at: March 8, 2026, 3:13 p.m.