Triple
T10143654
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kingdom of Kush |
E231646
|
entity |
| Predicate | majorSite |
P2462
|
FINISHED |
| Object | Nuri |
E418892
|
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: Nuri | Statement: [Kingdom of Kush, majorSite, Nuri]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nuri Context triple: [Kingdom of Kush, majorSite, Nuri]
-
A.
Nuri
chosen
Nuri is an ancient archaeological site in northern Sudan that served as a royal necropolis for Nubian kings and queens, featuring a significant concentration of Kushite pyramids.
-
B.
Nuri
Nuri is South Korea’s domestically developed three-stage orbital launch vehicle designed to place satellites into low Earth orbit.
-
C.
Kadir
Kadir is a masculine given name of Turkish origin commonly used in Turkey and among Turkish-speaking communities.
-
D.
Kadiria
Kadiria is a town and commune located within Bouira Province in northern Algeria.
-
E.
Ziya
Ziya is a masculine given name of Turkish origin, historically associated with notable figures such as sociologist and nationalist thinker Ziya Gökalp.
- 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_69ca848364f881908a24366a6feec1db |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cdeb28a1708190b46499dbe51a694a |
completed | April 2, 2026, 4:06 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e618b0bc8190bc1d6f15dac2708e |
completed | April 5, 2026, 10:45 p.m. |
Created at: March 30, 2026, 9:07 p.m.