Triple
T3545775
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Eric Bana |
E74991
|
entity |
| Predicate | portrayed |
P1668
|
FINISHED |
| Object |
John Meehan
John Meehan is the real-life conman and serial predator whose story inspired the podcast and TV series "Dirty John," in which he is portrayed by Eric Bana.
|
E370878
|
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: John Meehan | Statement: [Eric Bana, portrayed, John Meehan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Meehan Context triple: [Eric Bana, portrayed, John Meehan]
-
A.
Jonathan Corwin
Jonathan Corwin was a 17th-century Massachusetts magistrate best known as one of the judges who presided over the Salem witch trials.
-
B.
Matthew J. Driscoll
Matthew J. Driscoll is an American politician and public official from New York who has served as mayor of Syracuse and later held statewide leadership roles in transportation and infrastructure.
-
C.
Matthew F. Leonetti
Matthew F. Leonetti is an American cinematographer known for his work on numerous Hollywood films across action, comedy, and science fiction genres.
-
D.
Ron Feemster
Ron Feemster is a music producer known for his work on the album "Afrodisiac."
-
E.
Benjamin Barron
Benjamin Barron was the husband of Elizabeth Parris, who was historically associated with the Salem witch trials.
- 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: John Meehan Triple: [Eric Bana, portrayed, John Meehan]
Generated description
John Meehan is the real-life conman and serial predator whose story inspired the podcast and TV series "Dirty John," in which he is portrayed by Eric Bana.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Meehan Target entity description: John Meehan is the real-life conman and serial predator whose story inspired the podcast and TV series "Dirty John," in which he is portrayed by Eric Bana.
-
A.
Jonathan Corwin
Jonathan Corwin was a 17th-century Massachusetts magistrate best known as one of the judges who presided over the Salem witch trials.
-
B.
Matthew J. Driscoll
Matthew J. Driscoll is an American politician and public official from New York who has served as mayor of Syracuse and later held statewide leadership roles in transportation and infrastructure.
-
C.
Matthew F. Leonetti
Matthew F. Leonetti is an American cinematographer known for his work on numerous Hollywood films across action, comedy, and science fiction genres.
-
D.
Ron Feemster
Ron Feemster is a music producer known for his work on the album "Afrodisiac."
-
E.
Benjamin Barron
Benjamin Barron was the husband of Elizabeth Parris, who was historically associated with the Salem witch trials.
- 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_69ad85d33c6c819081d5ac1df13b5680 |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adbf77d938819095c72a88b5af644a |
completed | March 8, 2026, 6:27 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b402dfb0688190a65b41c8dc13ee97 |
completed | March 13, 2026, 12:28 p.m. |
| NEDg | Description generation | batch_69b403ebb5c0819098a48cfa9001c656 |
completed | March 13, 2026, 12:32 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4086ab034819086c5fa7d4b172d75 |
completed | March 13, 2026, 12:51 p.m. |
Created at: March 8, 2026, 3:20 p.m.