Triple
T4440863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Total Recall |
E95766
|
entity |
| Predicate | character |
P662
|
FINISHED |
| Object |
Vilos Cohaagen
Vilos Cohaagen is the ruthless and power-hungry corporate governor of Mars who serves as the main antagonist in the science fiction film "Total Recall."
|
E439216
|
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: Vilos Cohaagen | Statement: [Total Recall, character, Vilos Cohaagen]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Vilos Cohaagen Context triple: [Total Recall, character, Vilos Cohaagen]
-
A.
Ranon Ufgood
Ranon Ufgood is a character from the fantasy film "Willow," known as one of Willow Ufgood's children in the Nelwyn village.
-
B.
Garris Shrike
Garris Shrike is a character in the Star Wars Expanded Universe, known as the abusive criminal who raised and exploited a young Han Solo.
-
C.
Jost Vacano
Jost Vacano is a German cinematographer renowned for his dynamic, technically innovative work on films such as "Das Boot," "RoboCop," and other major international productions.
-
D.
Iron Felix
Iron Felix is the nickname of Felix Dzerzhinsky, the Soviet revolutionary who founded and led the Cheka, the Bolshevik secret police.
-
E.
Barret Zoph
Barret Zoph is a machine learning researcher known for his work on neural architecture search and contributions to deep learning at Google Brain.
- 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: Vilos Cohaagen Triple: [Total Recall, character, Vilos Cohaagen]
Generated description
Vilos Cohaagen is the ruthless and power-hungry corporate governor of Mars who serves as the main antagonist in the science fiction film "Total Recall."
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Vilos Cohaagen Target entity description: Vilos Cohaagen is the ruthless and power-hungry corporate governor of Mars who serves as the main antagonist in the science fiction film "Total Recall."
-
A.
Ranon Ufgood
Ranon Ufgood is a character from the fantasy film "Willow," known as one of Willow Ufgood's children in the Nelwyn village.
-
B.
Garris Shrike
Garris Shrike is a character in the Star Wars Expanded Universe, known as the abusive criminal who raised and exploited a young Han Solo.
-
C.
Jost Vacano
Jost Vacano is a German cinematographer renowned for his dynamic, technically innovative work on films such as "Das Boot," "RoboCop," and other major international productions.
-
D.
Iron Felix
Iron Felix is the nickname of Felix Dzerzhinsky, the Soviet revolutionary who founded and led the Cheka, the Bolshevik secret police.
-
E.
Barret Zoph
Barret Zoph is a machine learning researcher known for his work on neural architecture search and contributions to deep learning at Google Brain.
- 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_69b3453ea2b48190a26f154b3b8fece5 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355ac05e081908411089c05fc36bd |
completed | March 13, 2026, 12:09 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b61380fca08190bf036a7d82cee0e7 |
completed | March 15, 2026, 2:03 a.m. |
| NEDg | Description generation | batch_69b6143adefc81908f6c639906e0fd1a |
completed | March 15, 2026, 2:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b614b00dbc8190a7ea0477bedbc96a |
completed | March 15, 2026, 2:08 a.m. |
Created at: March 12, 2026, 11:32 p.m.