Triple
T5589249
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | NYPD Blue |
E146833
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
John Kelly
John Kelly is a tough, streetwise New York City detective and one of the original main characters on the television drama "NYPD Blue."
|
E536743
|
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 Kelly | Statement: [NYPD Blue, character, John Kelly]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: John Kelly Context triple: [NYPD Blue, character, John Kelly]
-
A.
John Kelly
John Kelly was the welfare recipient whose challenge to benefit termination procedures led to the landmark U.S. Supreme Court due process case Goldberg v. Kelly.
-
B.
John J. Kelly
John J. Kelly was a United States military serviceman whose distinguished service led to his burial at Golden Gate National Cemetery.
-
C.
John F. Kelly
John F. Kelly is a retired U.S. Marine Corps general who served in the Trump administration, including as White House Chief of Staff and Secretary of Homeland Security.
-
D.
Denis McDonough
Denis McDonough is an American political advisor who served as White House Chief of Staff under President Barack Obama.
-
E.
Richard Priebus
Richard Priebus is the father of former Republican National Committee chairman and White House Chief of Staff Reince Priebus.
- 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 Kelly Triple: [NYPD Blue, character, John Kelly]
Generated description
John Kelly is a tough, streetwise New York City detective and one of the original main characters on the television drama "NYPD Blue."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: John Kelly Target entity description: John Kelly is a tough, streetwise New York City detective and one of the original main characters on the television drama "NYPD Blue."
-
A.
John Kelly
John Kelly was the welfare recipient whose challenge to benefit termination procedures led to the landmark U.S. Supreme Court due process case Goldberg v. Kelly.
-
B.
John J. Kelly
John J. Kelly was a United States military serviceman whose distinguished service led to his burial at Golden Gate National Cemetery.
-
C.
John F. Kelly
John F. Kelly is a retired U.S. Marine Corps general who served in the Trump administration, including as White House Chief of Staff and Secretary of Homeland Security.
-
D.
Denis McDonough
Denis McDonough is an American political advisor who served as White House Chief of Staff under President Barack Obama.
-
E.
Richard Priebus
Richard Priebus is the father of former Republican National Committee chairman and White House Chief of Staff Reince Priebus.
- 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_69c009036c408190981a8d690b679b67 |
completed | March 22, 2026, 3:21 p.m. |
| NER | Named-entity recognition | batch_69c0209ff5d88190843b6d134390ab71 |
completed | March 22, 2026, 5:02 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69c04d342f7881908a79522692e8f7f9 |
completed | March 22, 2026, 8:12 p.m. |
| NEDg | Description generation | batch_69c04ed9159481909adeb9228ce59d0e |
completed | March 22, 2026, 8:19 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69c04f7856848190a835c3ee0a32f649 |
completed | March 22, 2026, 8:22 p.m. |
Created at: March 22, 2026, 3:38 p.m.