Triple
T20893060
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Aretas III of Nabatea |
E514456
|
entity |
| Predicate | successor |
P78
|
FINISHED |
| Object | Malichus I |
—
|
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: Malichus I | Statement: [Aretas III of Nabatea, successor, Malichus I]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Malichus I Context triple: [Aretas III of Nabatea, successor, Malichus I]
-
A.
Malichus I
chosen
Malichus I was a 1st-century BCE Nabataean king who ruled from Petra and helped consolidate the power of the Nabataean kingdom in the Levant.
-
B.
Malichus II
Malichus II was a 1st-century king of Nabatea who ruled from Petra and navigated his kingdom through the expanding influence of the Roman Empire.
-
C.
King Tzath I
King Tzath I was an early 6th-century monarch of Lazica known for his role in the region’s power struggles between the Byzantine and Sasanian Empires.
-
D.
King Abrazza
King Abrazza is a fictional monarch appearing as a character in the novel "Mardi" by Herman Melville.
-
E.
Monsieur Diafoirus
Monsieur Diafoirus is a pedantic and pompous physician in Molière’s comedy "Le Malade imaginaire," satirizing the outdated and dogmatic medical profession of his time.
- 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_69e0b4f7ebe48190952a85547a0f31a1 |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6d05fecd88190905a0ea80a24406a |
completed | April 21, 2026, 1:18 a.m. |
Created at: April 16, 2026, 12:46 p.m.