Triple
T23153192
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Smart People |
E578372
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Mark Jude Poirier
Mark Jude Poirier is an American author and screenwriter known for his literary fiction and for adapting his work and others’ into independent films.
|
E1574205
|
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: Mark Jude Poirier | Statement: [Smart People, screenwriter, Mark Jude Poirier]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mark Jude Poirier Context triple: [Smart People, screenwriter, Mark Jude Poirier]
-
A.
Michael Joncas
Michael Joncas is an American Catholic priest, theologian, and liturgical composer best known for his widely sung contemporary hymn "On Eagle’s Wings."
-
B.
Eric Thibault
Eric Thibault is a professional basketball coach best known for leading the WNBA’s Washington Mystics.
-
C.
David Beaubaire
David Beaubaire is a film producer known for his work on the movie "Fatherhood."
-
D.
Daniel Pellerin
Daniel Pellerin is a Canadian sound engineer and mixer renowned for his award-winning work in film and television.
-
E.
Joel Gosselin
Joel Gosselin is one of the Gosselin sextuplets who grew up in the public eye on the reality TV series "Jon & Kate Plus 8" (later "Kate Plus 8").
- 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: Mark Jude Poirier Triple: [Smart People, screenwriter, Mark Jude Poirier]
Generated description
Mark Jude Poirier is an American author and screenwriter known for his literary fiction and for adapting his work and others’ into independent films.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mark Jude Poirier Target entity description: Mark Jude Poirier is an American author and screenwriter known for his literary fiction and for adapting his work and others’ into independent films.
-
A.
Michael Joncas
Michael Joncas is an American Catholic priest, theologian, and liturgical composer best known for his widely sung contemporary hymn "On Eagle’s Wings."
-
B.
Eric Thibault
Eric Thibault is a professional basketball coach best known for leading the WNBA’s Washington Mystics.
-
C.
David Beaubaire
David Beaubaire is a film producer known for his work on the movie "Fatherhood."
-
D.
Daniel Pellerin
Daniel Pellerin is a Canadian sound engineer and mixer renowned for his award-winning work in film and television.
-
E.
Joel Gosselin
Joel Gosselin is one of the Gosselin sextuplets who grew up in the public eye on the reality TV series "Jon & Kate Plus 8" (later "Kate Plus 8").
- 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_69e245fb8de081908f0eba7b5fd75bc4 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f18efaa1fc81908fb1987dbf732f46 |
completed | April 29, 2026, 4:54 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0c309c3da48190b07c64b10fda58ff |
completed | May 19, 2026, 9:42 a.m. |
| NEDg | Description generation | batch_6a0c31dd458c8190b8e98870dd5e19c5 |
completed | May 19, 2026, 9:48 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0c325f5c248190b35e2c88b384ac31 |
completed | May 19, 2026, 9:50 a.m. |
Created at: April 17, 2026, 4:01 p.m.