Triple
T9152035
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Musawwarat es-Sufra |
E219608
|
entity |
| Predicate | dedicatedTo |
P500
|
FINISHED |
| Object | Apedemak |
E212975
|
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: Apedemak | Statement: [Musawwarat es-Sufra, dedicatedTo, Apedemak]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Apedemak Context triple: [Musawwarat es-Sufra, dedicatedTo, Apedemak]
-
A.
Apedemak
chosen
Apedemak is a lion-headed war and fertility god venerated in the ancient Nubian kingdom of Meroë, often associated with royal power and protection.
-
B.
Aptoryama
Aptoryama is a specific Vedic soma sacrifice ritual recognized as a variant form of the Somayajna.
-
C.
Anukis
Anukis is an ancient Egyptian goddess associated primarily with the Nile’s cataracts and southern frontier, often linked to fertility and protection.
-
D.
Kamsa
Kamsa is a tyrannical king in Hindu mythology, best known as the evil uncle and nemesis of Lord Krishna.
-
E.
Mantoro
Mantoro is a traditional Japanese lantern festival held at Kasuga Taisha Shrine in Nara, where thousands of stone and hanging lanterns are lit to create a spectacular nighttime illumination.
- 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_69ca83e25418819093c6503deeaf30de |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cca96cf4548190a3a45172f0e9d0ec |
completed | April 1, 2026, 5:13 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d04846544481909012f5c7fbbf3b0a |
completed | April 3, 2026, 11:07 p.m. |
Created at: March 30, 2026, 7:20 p.m.