Triple
T17406664
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sadiq Khan |
E423232
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Saadiya Khan
Saadiya Khan is a British solicitor best known as the wife of London Mayor Sadiq Khan.
|
E1267269
|
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: Saadiya Khan | Statement: [Sadiq Khan, spouse, Saadiya Khan]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Saadiya Khan Context triple: [Sadiq Khan, spouse, Saadiya Khan]
-
A.
Fakhr-un-Nissa
Fakhr-un-Nissa was the wife of Hyder Ali, the 18th-century de facto ruler of the Kingdom of Mysore in southern India.
-
B.
Sultan Nigar Khanum
Sultan Nigar Khanum was a Central Asian princess of the Chagatai-Moghul royal lineage, known primarily as a daughter of Yunus Khan of Moghulistan and for her dynastic connections in the Timurid-Moghul world.
-
C.
Ruqaiya Sultan Begum
Ruqaiya Sultan Begum was a Mughal empress and chief consort of Emperor Akbar, known for her high status and influence in the imperial court.
-
D.
Sultanum Begum
Sultanum Begum was a prominent Safavid royal consort and influential queen of Iran as the wife of Shah Tahmasp I.
-
E.
Kandahari Begum
Kandahari Begum was a Mughal princess and the first wife of Emperor Shah Jahan, known for her Timurid lineage and political significance in the Mughal court.
- 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: Saadiya Khan Triple: [Sadiq Khan, spouse, Saadiya Khan]
Generated description
Saadiya Khan is a British solicitor best known as the wife of London Mayor Sadiq Khan.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Saadiya Khan Target entity description: Saadiya Khan is a British solicitor best known as the wife of London Mayor Sadiq Khan.
-
A.
Fakhr-un-Nissa
Fakhr-un-Nissa was the wife of Hyder Ali, the 18th-century de facto ruler of the Kingdom of Mysore in southern India.
-
B.
Sultan Nigar Khanum
Sultan Nigar Khanum was a Central Asian princess of the Chagatai-Moghul royal lineage, known primarily as a daughter of Yunus Khan of Moghulistan and for her dynastic connections in the Timurid-Moghul world.
-
C.
Ruqaiya Sultan Begum
Ruqaiya Sultan Begum was a Mughal empress and chief consort of Emperor Akbar, known for her high status and influence in the imperial court.
-
D.
Sultanum Begum
Sultanum Begum was a prominent Safavid royal consort and influential queen of Iran as the wife of Shah Tahmasp I.
-
E.
Kandahari Begum
Kandahari Begum was a Mughal princess and the first wife of Emperor Shah Jahan, known for her Timurid lineage and political significance in the Mughal court.
- 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_69d889d7d27c819088486ce3f0627fa1 |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43b081ae08190b144e333a3a74b02 |
completed | April 19, 2026, 2:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a01a7f9bc508190aeae98b45c002d75 |
completed | May 11, 2026, 9:57 a.m. |
| NEDg | Description generation | batch_6a01a898ceb48190ba3d40c898b17158 |
completed | May 11, 2026, 9:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_6a01a9183410819083c8239e3ce38ea2 |
completed | May 11, 2026, 10:02 a.m. |
Created at: April 10, 2026, 5:45 a.m.