Triple
T8534658
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salima Hashmi |
E202047
|
entity |
| Predicate | parent |
P120
|
FINISHED |
| Object | Alys Faiz |
E199930
|
NE FINISHED |
How this triple was built (2 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: Alys Faiz | Statement: [Salima Hashmi, parent, Alys Faiz]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Alys Faiz Context triple: [Salima Hashmi, parent, Alys Faiz]
-
A.
Alys Faiz
chosen
Alys Faiz was a British-born Pakistani writer, journalist, and activist best known as the wife and literary companion of renowned Urdu poet Faiz Ahmed Faiz and for her own contributions to progressive cultural and political movements in Pakistan.
-
B.
Faiza Rauf
Faiza Rauf was an Egyptian princess and member of the Muhammad Ali dynasty, known as the daughter of King Fuad I of Egypt.
-
C.
Ayshah Tull
Ayshah Tull is a British journalist and television presenter best known for her work on BBC children’s news programme Newsround.
-
D.
Ayesha Foyez
Ayesha Foyez was the mother of renowned Bangladeshi writer, filmmaker, and dramatist Humayun Ahmed.
-
E.
Safia Minney
Safia Minney is a British social entrepreneur and founder of the ethical fashion brand People Tree, known for pioneering fair trade and sustainable practices in the fashion industry.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (3 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_69ca832355b08190b8b6a4ab4a4a3554 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe6a0ccd4819097b41d0dfb1c5018 |
completed | March 31, 2026, 3:22 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cea854e8c881909c62b29d999edde8 |
completed | April 2, 2026, 5:33 p.m. |
Created at: March 30, 2026, 6:17 p.m.