Triple
T21993586
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Invitation (2015 film) |
E543147
|
entity |
| Predicate | starring |
P1507
|
FINISHED |
| Object |
Jay Larson
Jay Larson is an American stand-up comedian and actor known for his work in film, television, and comedy specials.
|
E1512542
|
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: Jay Larson | Statement: [The Invitation (2015 film), starring, Jay Larson]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jay Larson Context triple: [The Invitation (2015 film), starring, Jay Larson]
-
A.
Jack Larson
Jack Larson was an American actor best known for playing Jimmy Olsen in the 1950s television series "Adventures of Superman."
-
B.
Neal Larson
Neal Larson is a paleontologist and fossil dealer best known for co-founding the Black Hills Institute of Geological Research, a leading private organization in fossil excavation and preparation.
-
C.
Keith Larsen
Keith Larsen was an American actor best known for his roles in 1950s Western films and television series.
-
D.
Jonathan Larsen
Jonathan Larsen is a New Zealand local government politician who serves as the deputy mayor of the Kaipara District.
-
E.
Matt Larson
Matt Larson is an Internet engineer and author known for his work on DNS standards and contributions to key IETF documents.
- 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: Jay Larson Triple: [The Invitation (2015 film), starring, Jay Larson]
Generated description
Jay Larson is an American stand-up comedian and actor known for his work in film, television, and comedy specials.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Jay Larson Target entity description: Jay Larson is an American stand-up comedian and actor known for his work in film, television, and comedy specials.
-
A.
Jack Larson
Jack Larson was an American actor best known for playing Jimmy Olsen in the 1950s television series "Adventures of Superman."
-
B.
Neal Larson
Neal Larson is a paleontologist and fossil dealer best known for co-founding the Black Hills Institute of Geological Research, a leading private organization in fossil excavation and preparation.
-
C.
Keith Larsen
Keith Larsen was an American actor best known for his roles in 1950s Western films and television series.
-
D.
Jonathan Larsen
Jonathan Larsen is a New Zealand local government politician who serves as the deputy mayor of the Kaipara District.
-
E.
Matt Larson
Matt Larson is an Internet engineer and author known for his work on DNS standards and contributions to key IETF documents.
- 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_69e11e2c814c8190837d072789000486 |
completed | April 16, 2026, 5:36 p.m. |
| NER | Named-entity recognition | batch_69f1270f77fc8190aadcc02760d65ac0 |
completed | April 28, 2026, 9:30 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a0a6d85f104819088dba8d0bf347fbe |
completed | May 18, 2026, 1:38 a.m. |
| NEDg | Description generation | batch_6a0a6e556f3c8190927d1c0cba23463c |
completed | May 18, 2026, 1:41 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0a6f3de2e88190824c9cc266c7ee8c |
completed | May 18, 2026, 1:45 a.m. |
Created at: April 16, 2026, 8:17 p.m.