Triple
T10627368
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Djehuty |
E250356
|
entity |
| Predicate | spouse |
P13
|
FINISHED |
| Object | Maʿat |
E250355
|
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: Maʿat | Statement: [Djehuty, spouse, Maʿat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Maʿat Context triple: [Djehuty, spouse, Maʿat]
-
A.
Ma'at
chosen
Ma'at is the ancient Egyptian concept and goddess of truth, justice, cosmic order, and harmony that underpinned both the universe and human society.
-
B.
Hathor
Hathor is an ancient Egyptian goddess associated with love, music, motherhood, fertility, and joy, often depicted as a cow or a woman with cow horns and a sun disk.
-
C.
Neith
Neith is an ancient Egyptian goddess associated with war, hunting, and weaving, often revered as a creator deity and protector of Lower Egypt.
-
D.
Heqet
Heqet is an ancient Egyptian frog-headed goddess associated primarily with fertility, childbirth, and the life-giving power of the Nile.
-
E.
Tefnut
Tefnut is an ancient Egyptian goddess primarily associated with moisture, rain, and fertility, often depicted as a lioness or a woman with a lioness’s head.
- 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_69d6aa5993448190a493b790b8f85010 |
completed | April 8, 2026, 7:19 p.m. |
| NER | Named-entity recognition | batch_69d6df8207f08190a6362a8ba00988b2 |
completed | April 8, 2026, 11:06 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d97a3e0e1481909c277be4c12b46ea |
completed | April 10, 2026, 10:31 p.m. |
Created at: April 8, 2026, 8:55 p.m.