Triple
T17575452
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Land of Frankincense |
E428052
|
entity |
| Predicate | near |
P350
|
FINISHED |
| Object | Salalah |
—
|
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: Salalah | Statement: [Land of Frankincense, near, Salalah]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Salalah Context triple: [Land of Frankincense, near, Salalah]
-
A.
Salalah
chosen
Salalah is a coastal city in southern Oman known for its monsoon-cooled climate, lush green landscapes, and role as a regional tourism and commercial hub.
-
B.
Ash Shihr
Ash Shihr is a coastal town in eastern Yemen historically known as a key port and commercial center in the Hadhramaut region.
-
C.
Aden
Aden is a strategic port city in Yemen located on the Gulf of Aden, historically significant as a major maritime hub and former British colonial stronghold.
-
D.
Aden
Aden was a small New York community that was permanently flooded and abandoned during the creation of the Neversink Reservoir in the mid-20th century.
-
E.
Salha
Salha is a Jordanian princess and member of the Hashemite royal family.
- 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_69d889e0385081908a04b66f4dd4bd0d |
completed | April 10, 2026, 5:25 a.m. |
| NER | Named-entity recognition | batch_69e463c88b3081908ddf6a2a12f6138e |
completed | April 19, 2026, 5:10 a.m. |
Created at: April 10, 2026, 5:50 a.m.