Triple
T23448766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Samsu-iluna |
E565614
|
entity |
| Predicate | territorialLosses |
P1701
|
FINISHED |
| Object | southern Mesopotamia |
—
|
LITERAL 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: southern Mesopotamia | Statement: [Samsu-iluna, territorialLosses, southern Mesopotamia]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: territorialLosses Context triple: [Samsu-iluna, territorialLosses, southern Mesopotamia]
-
A.
causedTerritorialLossesTo
Indicates that one entity was responsible for another entity losing control over some portion of its territory.
-
B.
residualTerritoriesLostBy
Indicates that certain remaining or leftover territories were lost by a specified entity.
-
C.
lostTerritoryBy
Indicates that one entity has had control or ownership of a territory taken away by another entity.
-
D.
lostSovereigntyIn
Indicates that an entity ceased to possess or exercise sovereign authority within a specified place or domain.
-
E.
territorialChange
chosen
Indicates a change in control or ownership of geographic territory from one entity to another, often as a result of political, legal, or military events.
- 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.