Triple
T19982300
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gemini Man |
E493845
|
entity |
| Predicate | mainCharacter |
P1183
|
FINISHED |
| Object |
Henry Brogan
Henry Brogan is an elite aging government assassin who becomes the target of a younger cloned version of himself in the science fiction action film "Gemini Man."
|
E1414168
|
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: Henry Brogan | Statement: [Gemini Man, mainCharacter, Henry Brogan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Henry Brogan Context triple: [Gemini Man, mainCharacter, Henry Brogan]
-
A.
Arthur Dignam
Arthur Dignam was an Australian actor known for his distinctive character roles in film, television, and theatre.
-
B.
William O’Leary
William O’Leary is an American actor best known for his role as Marty Taylor on the television sitcom "Home Improvement."
-
C.
Hugh O'Gorman
Hugh O'Gorman is an American actor best known for his role on the 1990s AMC television series "Remember WENN."
-
D.
John de Bermingham
John de Bermingham was an Anglo-Irish nobleman and military leader best known for defeating Edward Bruce and ending the Bruce campaign in Ireland in the early 14th century.
-
E.
Edward Keane
Edward Keane was an American character actor active in the early to mid-20th century, appearing in numerous films and serials, often in small or uncredited roles.
- 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: Henry Brogan Triple: [Gemini Man, mainCharacter, Henry Brogan]
Generated description
Henry Brogan is an elite aging government assassin who becomes the target of a younger cloned version of himself in the science fiction action film "Gemini Man."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Henry Brogan Target entity description: Henry Brogan is an elite aging government assassin who becomes the target of a younger cloned version of himself in the science fiction action film "Gemini Man."
-
A.
Arthur Dignam
Arthur Dignam was an Australian actor known for his distinctive character roles in film, television, and theatre.
-
B.
William O’Leary
William O’Leary is an American actor best known for his role as Marty Taylor on the television sitcom "Home Improvement."
-
C.
Hugh O'Gorman
Hugh O'Gorman is an American actor best known for his role on the 1990s AMC television series "Remember WENN."
-
D.
John de Bermingham
John de Bermingham was an Anglo-Irish nobleman and military leader best known for defeating Edward Bruce and ending the Bruce campaign in Ireland in the early 14th century.
-
E.
Edward Keane
Edward Keane was an American character actor active in the early to mid-20th century, appearing in numerous films and serials, often in small or uncredited roles.
- 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_69da626a67648190af9653832a3aeced |
completed | April 11, 2026, 3:02 p.m. |
| NER | Named-entity recognition | batch_69e65d13a8a88190bf5f4f697793f4c9 |
completed | April 20, 2026, 5:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a08345a83bc81908bd391f6835d8860 |
completed | May 16, 2026, 9:09 a.m. |
| NEDg | Description generation | batch_6a08353703b88190b8eef21650bad944 |
completed | May 16, 2026, 9:13 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0835c4c9f48190b4d568814729a7ca |
completed | May 16, 2026, 9:15 a.m. |
Created at: April 11, 2026, 3:28 p.m.