Triple
T1700161
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Zadig |
E36749
|
entity |
| Predicate | setting |
P1957
|
FINISHED |
| Object | Babylon |
E23692
|
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: Babylon | Statement: [Zadig, setting, Babylon]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Babylon Context triple: [Zadig, setting, Babylon]
-
A.
Babylon
Babylon is a town on the South Shore of Long Island in New York, known for its suburban communities, waterfront access, and role as a transportation hub.
-
B.
Babylon
chosen
Babylon was an ancient Mesopotamian city-state and imperial capital renowned for its monumental architecture, advanced culture, and central role in Near Eastern history and biblical tradition.
-
C.
Ashur
Ashur is an ancient Mesopotamian city in northern Iraq that served as the first capital and religious center of the Assyrian Empire.
-
D.
Nippur
Nippur was an ancient Sumerian city in Mesopotamia that served as a major religious center dedicated to the god Enlil.
-
E.
Sippar
Sippar was an important ancient Mesopotamian city, renowned as a religious and administrative center particularly associated with the sun god Shamash.
- 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_69a886163dec8190859c514232a37a05 |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69aa62d501188190b2e6ebf4d84471da |
completed | March 6, 2026, 5:15 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ad799d59a48190b1efb101c2a67e4f |
completed | March 8, 2026, 1:29 p.m. |
Created at: March 4, 2026, 7:30 p.m.