Triple
T17391543
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Qurna |
E422834
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Qurna |
—
|
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: Qurna | Statement: [Battle of Qurna, location, Qurna]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Qurna Context triple: [Battle of Qurna, location, Qurna]
-
A.
Qurna
chosen
Qurna is a town in southern Iraq near the confluence of the Tigris and Euphrates rivers, historically significant as a strategic site during World War I.
-
B.
Sekhen
Sekhen is an alternative name for the ancient Egyptian king Ka, an early ruler of the First Dynasty period.
-
C.
Kaa-Khem
Kaa-Khem is the local name for the Little Yenisei River, a tributary of the Yenisei flowing through the Tuva region of southern Siberia.
-
D.
Heryshef
Heryshef is an ancient Egyptian ram-headed god associated with creation, fertility, and the underworld, particularly venerated at Heracleopolis Magna.
-
E.
Sekhet-Aaru
Sekhet-Aaru is the ancient Egyptian paradise in the afterlife, envisioned as a lush, idealized reed field where the blessed dead lived in eternal peace and abundance.
- 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_69d889d710288190bf0f4762801fefae |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e43aba5398819096846bdeefde0788 |
completed | April 19, 2026, 2:15 a.m. |
Created at: April 10, 2026, 5:45 a.m.