Triple
T12667380
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tom Hanks as Colonel Tom Parker |
E302591
|
entity |
| Predicate | basedOn |
P98
|
FINISHED |
| Object |
Tom Parker
Tom Parker was the influential and controversial music manager best known for guiding Elvis Presley’s career to global superstardom.
|
E994401
|
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: Tom Parker | Statement: [Tom Hanks as Colonel Tom Parker, basedOn, Tom Parker]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Tom Parker Context triple: [Tom Hanks as Colonel Tom Parker, basedOn, Tom Parker]
-
A.
Tom Parker
Tom Parker is an enthusiastic and somewhat impulsive entrepreneur in Jane Austen’s unfinished novel "Sanditon," whose ambitions to develop the seaside resort drive much of the story’s events.
-
B.
Michael Parker
Michael Parker is a film editor best known for his work on the British comedy-drama "Made in Dagenham."
-
C.
Steve Parker
Steve Parker was an American film producer and manager best known for his long marriage to actress Shirley MacLaine and his work on international film projects.
-
D.
Brad Parker
Brad Parker is a screenwriter known for collaborating with Carey Van Dyke on film and television projects.
-
E.
John Whitesell
John Whitesell is an American television and film director and producer known for his work on various TV series and feature comedies.
- 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: Tom Parker Triple: [Tom Hanks as Colonel Tom Parker, basedOn, Tom Parker]
Generated description
Tom Parker was the influential and controversial music manager best known for guiding Elvis Presley’s career to global superstardom.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Tom Parker Target entity description: Tom Parker was the influential and controversial music manager best known for guiding Elvis Presley’s career to global superstardom.
-
A.
Tom Parker
Tom Parker is an enthusiastic and somewhat impulsive entrepreneur in Jane Austen’s unfinished novel "Sanditon," whose ambitions to develop the seaside resort drive much of the story’s events.
-
B.
Michael Parker
Michael Parker is a film editor best known for his work on the British comedy-drama "Made in Dagenham."
-
C.
Steve Parker
Steve Parker was an American film producer and manager best known for his long marriage to actress Shirley MacLaine and his work on international film projects.
-
D.
Brad Parker
Brad Parker is a screenwriter known for collaborating with Carey Van Dyke on film and television projects.
-
E.
John Whitesell
John Whitesell is an American television and film director and producer known for his work on various TV series and feature comedies.
- 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_69d7bded71a88190bb76e2413af9ea66 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d96181c40481908f3e2717f5472b85 |
completed | April 10, 2026, 8:45 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69f6688bfc048190970d281e66c34cdc |
completed | May 2, 2026, 9:11 p.m. |
| NEDg | Description generation | batch_69f6695372688190b09a2bb2e58cb546 |
completed | May 2, 2026, 9:14 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69f669fe4bc48190adba50ad58b10c45 |
completed | May 2, 2026, 9:17 p.m. |
Created at: April 9, 2026, 5:20 p.m.