Triple
T22480856
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Umm el-Qaab necropolis |
E555758
|
entity |
| Predicate | burialPlaceOf |
P196
|
FINISHED |
| Object | Semerkhet |
—
|
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: Semerkhet | Statement: [Umm el-Qaab necropolis, burialPlaceOf, Semerkhet]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Semerkhet Context triple: [Umm el-Qaab necropolis, burialPlaceOf, Semerkhet]
-
A.
Semerkhet
chosen
Semerkhet was an early dynastic Egyptian pharaoh of the First Dynasty, known from archaeological records and king lists as one of the successors of the unifier-kings of ancient Egypt.
-
B.
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.
-
C.
Saqar
Saqar is a term in the Qur'an referring to a severe level of Hell associated with intense punishment for disbelievers.
-
D.
Sekhen
Sekhen is an alternative name for the ancient Egyptian king Ka, an early ruler of the First Dynasty period.
-
E.
Tuna el-Gebel
Tuna el-Gebel is an extensive ancient Egyptian necropolis and archaeological site renowned for its tombs, catacombs, and temples spanning the Late Period through the Greco-Roman era.
- 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_69e11e53897c819088863779f8c50bb0 |
completed | April 16, 2026, 5:37 p.m. |
| NER | Named-entity recognition | batch_69f15c397b248190b36c2fbfa6489693 |
completed | April 29, 2026, 1:17 a.m. |
Created at: April 16, 2026, 8:49 p.m.