Triple
T22824473
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sultan Malik Shah I |
E565314
|
entity |
| Predicate | issue |
P2239
|
FINISHED |
| Object | Ahmad Sanjar |
—
|
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: Ahmad Sanjar | Statement: [Sultan Malik Shah I, issue, Ahmad Sanjar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Ahmad Sanjar Context triple: [Sultan Malik Shah I, issue, Ahmad Sanjar]
-
A.
Sultan Ahmad Sanjar
chosen
Sultan Ahmad Sanjar was a prominent 12th-century Seljuk sultan who ruled Khorasan and later much of the Seljuk Empire, known for his military campaigns, political struggles, and eventual defeat by the Khwarazmians and Oghuz Turks.
-
B.
Baha al-Dawla
Baha al-Dawla was a prominent 10th–11th century Buyid ruler who governed parts of Iran and Iraq during the later phase of the dynasty’s power.
-
C.
Alāʾ al-Dīn
Alāʾ al-Dīn was the honorific regnal name of Kayqubad II, a 13th-century Seljuk sultan of Rum.
-
D.
Shams al-Dawla
Shams al-Dawla was a Buyid dynasty ruler who governed parts of western Iran in the late 10th and early 11th centuries.
-
E.
Nur al-Din Muhammad
Nur al-Din Muhammad was a medieval Muslim ruler from the Artuqid dynasty who governed the important Anatolian city of Diyarbakır.
- F. None of above.
- G. Unsure - the case is ambiguous/there is not enough information to decide.
Provenance (2 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_69e2458426188190b58b8ab4844fe420 |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f17dd34a248190881f2bccdd9aedce |
completed | April 29, 2026, 3:41 a.m. |
Created at: April 17, 2026, 3:34 p.m.