Triple
T23413310
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hormizd I |
E560137
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Denag |
—
|
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: Denag | Statement: [Hormizd I, spouse, Denag]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Denag Context triple: [Hormizd I, spouse, Denag]
-
A.
Denag
chosen
Denag was a Sasanian queen and royal consort, best known as the mother of the 3rd-century king Hormizd I of the Sasanian Empire.
-
B.
Denjaka
Denjaka is an elite Indonesian naval special forces unit specializing in maritime counter-terrorism, sabotage, and underwater operations.
-
C.
Deniyaya
Deniyaya is a small town in southern Sri Lanka known as a primary gateway to the Sinharaja Forest Reserve, a UNESCO-listed tropical rainforest.
-
D.
Denyen
The Denyen were an enigmatic Late Bronze Age people, often identified as one of the Sea Peoples who disrupted Eastern Mediterranean civilizations around the 12th century BCE.
-
E.
Dagana
Dagana is a historic town in the Senegal River valley that served as an important center in the former Futa Tooro region.
- 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_69e2454b3a5881909c64773dc8a5d289 |
completed | April 17, 2026, 2:35 p.m. |
| NER | Named-entity recognition | batch_69f1a513502881909f33a43bfd5e63a7 |
completed | April 29, 2026, 6:28 a.m. |
Created at: April 17, 2026, 5:39 p.m.