Triple
T3378302
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Spyfall |
E71118
|
entity |
| Predicate | featuresCharacter |
P626
|
FINISHED |
| Object |
Yasmin Khan
Yasmin Khan is a companion of the Thirteenth Doctor in the long-running British science fiction television series Doctor Who.
|
E354207
|
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: Yasmin Khan | Statement: [Spyfall, featuresCharacter, Yasmin Khan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Yasmin Khan Context triple: [Spyfall, featuresCharacter, Yasmin Khan]
-
A.
Nadia Sawalha
Nadia Sawalha is a British actress and television presenter best known for her long-running role as a panellist on the daytime talk show "Loose Women."
-
B.
Jasmin Mohammed
Jasmin Mohammed is a writer known for authoring the work titled "Who Shot Ya?".
-
C.
Farah Diba
Farah Diba is the former Empress (Shahbanu) of Iran, known for her marriage to Shah Mohammad Reza Pahlavi and her prominent role in Iran’s cultural and social modernization before the 1979 revolution.
-
D.
Naheed Mirza
Naheed Mirza was the wife of Iskander Mirza, the first President of Pakistan.
-
E.
Yasmin Sooka
Yasmin Sooka is a South African human rights lawyer and activist best known for her work on truth, justice, and post-conflict reconciliation, including serving on South Africa’s Truth and Reconciliation Commission.
- 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: Yasmin Khan Triple: [Spyfall, featuresCharacter, Yasmin Khan]
Generated description
Yasmin Khan is a companion of the Thirteenth Doctor in the long-running British science fiction television series Doctor Who.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Yasmin Khan Target entity description: Yasmin Khan is a companion of the Thirteenth Doctor in the long-running British science fiction television series Doctor Who.
-
A.
Nadia Sawalha
Nadia Sawalha is a British actress and television presenter best known for her long-running role as a panellist on the daytime talk show "Loose Women."
-
B.
Jasmin Mohammed
Jasmin Mohammed is a writer known for authoring the work titled "Who Shot Ya?".
-
C.
Farah Diba
Farah Diba is the former Empress (Shahbanu) of Iran, known for her marriage to Shah Mohammad Reza Pahlavi and her prominent role in Iran’s cultural and social modernization before the 1979 revolution.
-
D.
Naheed Mirza
Naheed Mirza was the wife of Iskander Mirza, the first President of Pakistan.
-
E.
Yasmin Sooka
Yasmin Sooka is a South African human rights lawyer and activist best known for her work on truth, justice, and post-conflict reconciliation, including serving on South Africa’s Truth and Reconciliation Commission.
- 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_69ad85a7f80c8190a05e43013f298942 |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb2eacb5c81908071a1dacc9a897a |
completed | March 8, 2026, 5:33 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b3344c0698819082d856d8be7f2c18 |
completed | March 12, 2026, 9:46 p.m. |
| NEDg | Description generation | batch_69b334e5171c8190a01bb6fef5644825 |
completed | March 12, 2026, 9:49 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69b3390c50b08190b6239b5f0d1eb4ba |
completed | March 12, 2026, 10:07 p.m. |
Created at: March 8, 2026, 3:14 p.m.