Triple
T11499026
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Shrek 2 |
E272615
|
entity |
| Predicate | screenwriter |
P2831
|
FINISHED |
| Object |
Joe Stillman
Joe Stillman is an American screenwriter best known for his work on the hit animated Shrek films and various television comedies.
|
E929288
|
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: Joe Stillman | Statement: [Shrek 2, screenwriter, Joe Stillman]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Joe Stillman Context triple: [Shrek 2, screenwriter, Joe Stillman]
-
A.
Tom Stillman
Tom Stillman is an American businessman best known as the principal owner and chairman of the NHL’s St. Louis Blues.
-
B.
John Reiser
John Reiser is a software developer best known for creating the UPX (Ultimate Packer for Executables) compression tool.
-
C.
Johnny Gandelsman
Johnny Gandelsman is a Grammy-winning violinist and producer known for his work with ensembles like Brooklyn Rider and the Silk Road Ensemble, as well as for his innovative solo projects.
-
D.
Joe Schoen
Joe Schoen is an American football executive best known as the general manager who helped lead the New York Giants’ recent roster rebuild and organizational turnaround.
-
E.
Larry Mann
Larry Mann is the husband of renowned American photographer Sally Mann, often appearing as a subject in her intimate family portraits.
- 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: Joe Stillman Triple: [Shrek 2, screenwriter, Joe Stillman]
Generated description
Joe Stillman is an American screenwriter best known for his work on the hit animated Shrek films and various television comedies.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Joe Stillman Target entity description: Joe Stillman is an American screenwriter best known for his work on the hit animated Shrek films and various television comedies.
-
A.
Tom Stillman
Tom Stillman is an American businessman best known as the principal owner and chairman of the NHL’s St. Louis Blues.
-
B.
John Reiser
John Reiser is a software developer best known for creating the UPX (Ultimate Packer for Executables) compression tool.
-
C.
Johnny Gandelsman
Johnny Gandelsman is a Grammy-winning violinist and producer known for his work with ensembles like Brooklyn Rider and the Silk Road Ensemble, as well as for his innovative solo projects.
-
D.
Joe Schoen
Joe Schoen is an American football executive best known as the general manager who helped lead the New York Giants’ recent roster rebuild and organizational turnaround.
-
E.
Larry Mann
Larry Mann is the husband of renowned American photographer Sally Mann, often appearing as a subject in her intimate family portraits.
- 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_69d6aae1b09881909ce2ded3fa0c14fa |
completed | April 8, 2026, 7:22 p.m. |
| NER | Named-entity recognition | batch_69d85de27db081909ccdb4ab0ef75bdb |
completed | April 10, 2026, 2:18 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e604aa9e3c8190ad86e4d05a67c8ac |
completed | April 20, 2026, 10:49 a.m. |
| NEDg | Description generation | batch_69e610a82c308190927158dbd566b0d4 |
completed | April 20, 2026, 11:40 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69e61853a3b48190b0d132761e9be69c |
completed | April 20, 2026, 12:13 p.m. |
Created at: April 8, 2026, 9:36 p.m.