Triple
T4413905
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salam |
E94917
|
entity |
| Predicate | hasVariant |
P455
|
FINISHED |
| Object | Al-Salam |
E436975
|
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: Al-Salam | Statement: [Salam, hasVariant, Al-Salam]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Al-Salam Context triple: [Salam, hasVariant, Al-Salam]
-
A.
As-Salam
chosen
As-Salam is one of the names of God in Islam, signifying "The Source of Peace" and embodying divine safety, harmony, and well-being.
-
B.
Sallah
Sallah is a jovial, resourceful Egyptian excavator and close ally of Indiana Jones who helps him navigate dangerous archaeological adventures.
-
C.
As-Samad
As-Samad is one of the names of Allah in Islam, signifying the One who is absolutely self-sufficient, eternally depended upon by all creation, and free of all need.
-
D.
Al-Wahid
Al-Wahid is one of the names of God in Islamic theology, emphasizing His absolute oneness and uniqueness as the sole divine being.
-
E.
Al-Hareeq
Al-Hareeq is a town in central Saudi Arabia known for its agricultural activity, particularly date palm cultivation, within the Riyadh region.
- 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_69b34539638c8190abfea3eb29425210 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b354e940d48190b49cca6796d60de4 |
completed | March 13, 2026, 12:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b627eb49308190a6830cbc52ad45cf |
completed | March 15, 2026, 3:30 a.m. |
Created at: March 12, 2026, 11:29 p.m.