Triple
T17343992
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Great Sith War |
E421134
|
entity |
| Predicate | leader |
P981
|
FINISHED |
| Object |
Aleema Keto
Aleema Keto was a powerful and manipulative Sith sorceress from the Star Wars Expanded Universe who played a key role in instigating and escalating the Great Sith War.
|
E1263763
|
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: Aleema Keto | Statement: [Great Sith War, leader, Aleema Keto]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Aleema Keto Context triple: [Great Sith War, leader, Aleema Keto]
-
A.
Kaleen
Kaleen is a residential suburb in the Belconnen district of Canberra, in the Australian Capital Territory.
-
B.
Eveyla Akuru
Eveyla Akuru is an ancient script formerly used to write the Dhivehi language of the Maldives before it was replaced by the modern Thaana script.
-
C.
Kareme
Kareme is the historical name of the Greek town now known as Koropi in the region of East Attica.
-
D.
Alya Kattan
Alya Kattan is a beauty entrepreneur best known for co-founding and helping build the global cosmetics brand Huda Beauty alongside her sister Huda Kattan.
-
E.
Kamaal
Kamaal is a masculine given name, commonly used in South Asian and Middle Eastern cultures, that conveys meanings related to perfection or excellence.
- 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: Aleema Keto Triple: [Great Sith War, leader, Aleema Keto]
Generated description
Aleema Keto was a powerful and manipulative Sith sorceress from the Star Wars Expanded Universe who played a key role in instigating and escalating the Great Sith War.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Aleema Keto Target entity description: Aleema Keto was a powerful and manipulative Sith sorceress from the Star Wars Expanded Universe who played a key role in instigating and escalating the Great Sith War.
-
A.
Kaleen
Kaleen is a residential suburb in the Belconnen district of Canberra, in the Australian Capital Territory.
-
B.
Eveyla Akuru
Eveyla Akuru is an ancient script formerly used to write the Dhivehi language of the Maldives before it was replaced by the modern Thaana script.
-
C.
Kareme
Kareme is the historical name of the Greek town now known as Koropi in the region of East Attica.
-
D.
Alya Kattan
Alya Kattan is a beauty entrepreneur best known for co-founding and helping build the global cosmetics brand Huda Beauty alongside her sister Huda Kattan.
-
E.
Kamaal
Kamaal is a masculine given name, commonly used in South Asian and Middle Eastern cultures, that conveys meanings related to perfection or excellence.
- 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_69d889d3adc881909319f1edb8d2a956 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43a27a350819086faf12e6bf9f0e2 |
completed | April 19, 2026, 2:12 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a018c5a7c308190b478918b66a4276c |
completed | May 11, 2026, 7:59 a.m. |
| NEDg | Description generation | batch_6a018d67ddd081909d227ae3405415ee |
completed | May 11, 2026, 8:03 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a0192dfff1881909aa87f5d23cda870 |
completed | May 11, 2026, 8:27 a.m. |
Created at: April 10, 2026, 5:44 a.m.