Triple
T25456523
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | شيبة الحمد |
E637928
|
entity |
| Predicate | الجد للأم |
P158539
|
FINISHED |
| Object | عمرو بن زيد من بني النجار من الخزرج |
—
|
NE NERFINISHED |
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: عمرو بن زيد من بني النجار من الخزرج | Statement: [شيبة الحمد, الجد للأم, عمرو بن زيد من بني النجار من الخزرج]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: الجد للأم Context triple: [شيبة الحمد, الجد للأم, عمرو بن زيد من بني النجار من الخزرج]
-
A.
الجد
chosen
Indicates a grandparent relationship, where one entity is the grandfather of another.
-
B.
الحفيد
Indicates a grandchild relationship, where one entity is the descendant (grandson or granddaughter) of another entity’s child.
-
C.
الجد_للأم_أو_الأب
Indicates a grandparent relationship where the person is the grandfather or grandmother of someone, whether through the mother or the father.
-
D.
الجيل
Indicates a generational relationship, linking entities as belonging to the same generation or specifying that one entity is a particular generation relative to another.
-
E.
مهنة الأب
Indicates the occupation or profession held by the father.
- F. None of above.
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_69e75db8bab08190baca80b4a8c315fd |
completed | April 21, 2026, 11:21 a.m. |
| NER | Named-entity recognition | batch_69f5f72756748190aa315cc00882a798 |
completed | May 2, 2026, 1:07 p.m. |
| PD | Predicate disambiguation | batch_69f49377411c8190b2188de444d76795 |
completed | May 1, 2026, 11:50 a.m. |
Created at: April 21, 2026, 2:10 p.m.