Triple
T8925988
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Gudea |
E212539
|
entity |
| Predicate | worshippedDeity |
P1194
|
FINISHED |
| Object | Nanshe |
E770332
|
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: Nanshe | Statement: [Gudea, worshippedDeity, Nanshe]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nanshe Context triple: [Gudea, worshippedDeity, Nanshe]
-
A.
Nanshe
chosen
Nanshe is a Mesopotamian goddess associated primarily with social justice, divination, and the protection of the vulnerable.
-
B.
Ur-Nanshe
Ur-Nanshe was an early dynastic king of the Sumerian city-state of Lagash, known for temple construction and establishing Lagash as a significant regional power.
-
C.
Enheduanna
Enheduanna was an Akkadian high priestess and poet from the 23rd century BCE, widely regarded as the earliest known named author in world history.
-
D.
Seshemetka
Seshemetka was an early ancient Egyptian queen consort of the 1st Dynasty, known primarily as a wife of King Djer.
-
E.
Tashmetu-sharrat
Tashmetu-sharrat was a Neo-Assyrian queen and consort of King Sennacherib, known from royal inscriptions and administrative records of his reign.
- 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_69ca839481d48190b42b037e0d0f636c |
completed | March 30, 2026, 2:07 p.m. |
| NER | Named-entity recognition | batch_69cc66700fb48190874563e535f20437 |
completed | April 1, 2026, 12:27 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69cfdb856560819085132abe9ef94819 |
completed | April 3, 2026, 3:23 p.m. |
Created at: March 30, 2026, 6:57 p.m.