Triple
T19712511
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tell Brak |
E473383
|
entity |
| Predicate | hasAncientName |
P20952
|
FINISHED |
| Object | Nawar |
—
|
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: Nawar | Statement: [Tell Brak, hasAncientName, Nawar]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Nawar Context triple: [Tell Brak, hasAncientName, Nawar]
-
A.
Nawar
chosen
Nawar are a traditionally itinerant ethnic group of the Middle East, culturally and linguistically related to the Dom people and often associated with peripatetic trades and marginalized social status.
-
B.
Nawa
Nawa is a town in southern Syria historically known as the birthplace of the prominent Islamic scholar Imam Al-Nawawi.
-
C.
Nawi
Nawi is a brave young warrior in the Agojie, the all-female military regiment of the Kingdom of Dahomey, whose journey of training, loyalty, and self-discovery drives the narrative of *The Woman King*.
-
D.
Nawda
Nawda is an indigenous Gur language spoken primarily in parts of Burkina Faso and neighboring West African regions.
-
E.
Nawuri
Nawuri is a Guang language spoken primarily by the Nawuri people in northern Ghana.
- 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_69d8e516dd048190a0b6c93ea3e71f58 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e6440a0f2c8190803ace7f6b4ed6e9 |
completed | April 20, 2026, 3:19 p.m. |
Created at: April 10, 2026, 1:46 p.m.