Triple
T23448778
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samsu-iluna |
E565614
|
entity |
| Predicate | motherLanguageRegion |
P50963
|
FINISHED |
| Object | Mesopotamia |
—
|
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: Mesopotamia | Statement: [Samsu-iluna, motherLanguageRegion, Mesopotamia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: motherLanguageRegion Context triple: [Samsu-iluna, motherLanguageRegion, Mesopotamia]
-
A.
motherTongueRegion
chosen
Indicates the geographic region where an entity’s native or primary language is predominantly spoken or originates.
-
B.
regionLanguage
Indicates that a particular language is used or officially recognized within a specific geographic region.
-
C.
subjectLanguageRegion
Indicates that the subject is associated with or uses a language specific to a particular geographic region.
-
D.
formerLanguageRegion
Indicates that a region previously used a particular language as significant or dominant, but no longer does so.
-
E.
sourceLanguageRegion
Indicates the geographic or cultural region associated with the language from which something originates or is derived.
- F. None of above.
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_69e24584f9488190bb32730bd2ce023e |
completed | April 17, 2026, 2:36 p.m. |
| NER | Named-entity recognition | batch_69f1a64b27988190b4722425da964407 |
completed | April 29, 2026, 6:33 a.m. |
| PD | Predicate disambiguation | batch_69f06201d33481909b5fd7b92d03e658 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 5:52 p.m.