Triple
T4455509
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Siege of Samaria |
E97711
|
entity |
| Predicate | locatedIn |
P40
|
FINISHED |
| Object | Samaria |
E28574
|
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: Samaria | Statement: [Siege of Samaria, locatedIn, Samaria]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Samaria Context triple: [Siege of Samaria, locatedIn, Samaria]
-
A.
Samaria
chosen
Samaria is a historical region in the central highlands of ancient Israel and the West Bank, known as the capital area of the northern Kingdom of Israel and a significant biblical and archaeological site.
-
B.
Judea
Judea was an ancient region in the Levant, centered around Jerusalem, that served as a major cultural and religious heartland for the Jewish people and the early development of Christianity.
-
C.
Gilʿad
Gilʿad is a biblical region east of the Jordan River, traditionally associated with the ancient Israelite tribes and noted for its rugged terrain and balm-producing plants.
-
D.
ערבה
ערבה היא בקעה מדברית רחבת ידיים בדרום ארץ ישראל וירדן, המשתרעת בין ים המלח למפרץ אילת.
-
E.
Madyan
Madyan is a scenic hill town and tourist resort in Pakistan’s Swat Valley, known for its cool climate, river views, and surrounding mountains.
- 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_69b3454777808190b78aa9047ba1f018 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b355f79ca481909338dda9f4f7171f |
completed | March 13, 2026, 12:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b62822643c8190a0af89f2896fde3e |
completed | March 15, 2026, 3:31 a.m. |
Created at: March 12, 2026, 11:33 p.m.