Triple
T13915748
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chagataid dynasty |
E334615
|
entity |
| Predicate | capital |
P234
|
FINISHED |
| Object | Almaliq |
E334614
|
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: Almaliq | Statement: [Chagataid dynasty, capital, Almaliq]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Almaliq Context triple: [Chagataid dynasty, capital, Almaliq]
-
A.
Almaliq
chosen
Almaliq was a prominent medieval Central Asian city that served as a key political and commercial center along the Silk Road.
-
B.
Jalalaqsi
Jalalaqsi is a town in central Somalia that serves as a local administrative and commercial center within the Hirshabelle State.
-
C.
Moynaq
Moynaq is a former fishing town in western Uzbekistan that became infamous as a symbol of environmental disaster after the Aral Sea largely dried up, leaving the settlement stranded far from the receding shoreline.
-
D.
Almalyk
Almalyk is a historic Central Asian city, now located in southeastern Kazakhstan, that was once an important Silk Road trading center.
-
E.
Almaly
Almaly is a central underground metro station in Almaty, Kazakhstan, serving the city's rapid transit system.
- 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_69d81c5eaa9c819083b1ff8689179565 |
completed | April 9, 2026, 9:38 p.m. |
| NER | Named-entity recognition | batch_69de27260ae08190be45b4b15898e365 |
completed | April 14, 2026, 11:38 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fba1c26ba08190b19560123691fda4 |
completed | May 6, 2026, 8:17 p.m. |
Created at: April 9, 2026, 10:16 p.m.