Triple
T19106822
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Coins of the Ottoman Empire |
E467677
|
entity |
| Predicate | denominationType |
P5805
|
FINISHED |
| Object | akçe |
—
|
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: akçe | Statement: [Coins of the Ottoman Empire, denominationType, akçe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: akçe Context triple: [Coins of the Ottoman Empire, denominationType, akçe]
-
A.
akçe
chosen
The akçe was a small silver coin that served as the basic monetary unit of the early Ottoman Empire before being replaced by larger denominations like the kuruş.
-
B.
Akçe
Akçe was the primary silver coin and monetary unit of the Ottoman Empire for several centuries, widely used across its territories.
-
C.
Acımak
Acımak is a Turkish novel by Reşat Nuri Güntekin that explores themes of compassion, regret, and the complexities of human relationships.
-
D.
ack
ack is a command-line search tool for programmers that improves on grep with language-aware searching, sensible defaults, and features tailored for codebases.
-
E.
AKJ
AKJ is the ICAO airline designator assigned to Akasa Air, a low-cost carrier based in India.
- 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_69d8dd06a26481908039e2a1bae8c597 |
completed | April 10, 2026, 11:20 a.m. |
| NER | Named-entity recognition | batch_69e5e391245c8190b1393577b61c4f76 |
completed | April 20, 2026, 8:28 a.m. |
Created at: April 10, 2026, 12:04 p.m.