Triple
T25754282
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | الزبير بن عبد المطلب |
E648548
|
entity |
| Predicate | الدور في حلف الفضول |
P159233
|
FINISHED |
| Object | من الموقعين على حلف الفضول |
—
|
LITERAL 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: من الموقعين على حلف الفضول | Statement: [الزبير بن عبد المطلب, الدور في حلف الفضول, من الموقعين على حلف الفضول]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: الدور في حلف الفضول Context triple: [الزبير بن عبد المطلب, الدور في حلف الفضول, من الموقعين على حلف الفضول]
-
A.
الدور في حلف الفضول
chosen
Indicates the role or participation an entity had in the Hilf al-Fudul alliance.
-
B.
عدد الحروف
Indicates the relationship that specifies the number of letters contained in a given word or text.
-
C.
الحفيد
Indicates a grandchild relationship, where one entity is the descendant (grandson or granddaughter) of another entity’s child.
-
D.
سبب التسمية
Indicates the reason or cause behind assigning a particular name to something.
-
E.
من السور
Indicates a relationship where something originates from, is taken from, or is part of a specific wall or fence.
- 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_69e7ab314d788190b3abe19e114080e1 |
completed | April 21, 2026, 4:52 p.m. |
| NER | Named-entity recognition | batch_69f5fd81788c819096c045e9ef3ffc08 |
completed | May 2, 2026, 1:34 p.m. |
| PD | Predicate disambiguation | batch_69f4a0fed15881909b789251fe5d8d45 |
completed | May 1, 2026, 12:47 p.m. |
Created at: April 22, 2026, 4:38 a.m.