Triple
T10568862
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Wasfi al-Tal |
E249424
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object |
Sadia al-Tal
Sadia al-Tal is known primarily as the wife of the late Jordanian Prime Minister Wasfi al-Tal.
|
E871895
|
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: Sadia al-Tal | Statement: [Wasfi al-Tal, spouse, Sadia al-Tal]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sadia al-Tal Context triple: [Wasfi al-Tal, spouse, Sadia al-Tal]
-
A.
Latifa al-Zayyat
Latifa al-Zayyat was an influential Egyptian novelist, critic, and feminist intellectual best known for her pioneering role in modern Arabic literature and women’s rights.
-
B.
Aisha al-Mashal
Aisha al-Mashal is known primarily as the wife of senior Hamas political leader Khaled Mashal.
-
C.
Zaynab bint Mazun
Zaynab bint Mazun was an early Muslim woman from the first generation of Islam, known primarily as the mother of Hafsa bint Umar, one of the wives of the Prophet Muhammad.
-
D.
Marj al-Saffar
Marj al-Saffar is a historic plain in southern Syria that served as a key battlefield and strategic corridor between Damascus and the surrounding regions.
-
E.
Safa Zaki
Safa Zaki is a cognitive psychologist and academic leader who became the first woman to serve as president of Bowdoin College.
- 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: Sadia al-Tal Triple: [Wasfi al-Tal, spouse, Sadia al-Tal]
Generated description
Sadia al-Tal is known primarily as the wife of the late Jordanian Prime Minister Wasfi al-Tal.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sadia al-Tal Target entity description: Sadia al-Tal is known primarily as the wife of the late Jordanian Prime Minister Wasfi al-Tal.
-
A.
Latifa al-Zayyat
Latifa al-Zayyat was an influential Egyptian novelist, critic, and feminist intellectual best known for her pioneering role in modern Arabic literature and women’s rights.
-
B.
Aisha al-Mashal
Aisha al-Mashal is known primarily as the wife of senior Hamas political leader Khaled Mashal.
-
C.
Zaynab bint Mazun
Zaynab bint Mazun was an early Muslim woman from the first generation of Islam, known primarily as the mother of Hafsa bint Umar, one of the wives of the Prophet Muhammad.
-
D.
Marj al-Saffar
Marj al-Saffar is a historic plain in southern Syria that served as a key battlefield and strategic corridor between Damascus and the surrounding regions.
-
E.
Safa Zaki
Safa Zaki is a cognitive psychologist and academic leader who became the first woman to serve as president of Bowdoin College.
- 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_69d381c8bd708190acf3d275c908251e |
completed | April 6, 2026, 9:50 a.m. |
| NER | Named-entity recognition | batch_69d5272ff53c8190ae7c399d49b585f5 |
completed | April 7, 2026, 3:48 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d94b4c26ec8190910efdf4a236d654 |
completed | April 10, 2026, 7:11 p.m. |
| NEDg | Description generation | batch_69d94e2f16788190bec54b250dad09a9 |
completed | April 10, 2026, 7:23 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69d9518517608190b5036694b83f5f58 |
completed | April 10, 2026, 7:37 p.m. |
Created at: April 6, 2026, 12:37 p.m.