Triple
T10153936
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Battle of Cetate |
E232720
|
entity |
| Predicate | location |
P40
|
FINISHED |
| Object | Cetate |
E265132
|
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: Cetate | Statement: [Battle of Cetate, location, Cetate]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Cetate Context triple: [Battle of Cetate, location, Cetate]
-
A.
Satala
Satala is a coastal village and harbor area on the island of Tutuila in American Samoa, known historically as a commercial and maritime hub near the capital region.
-
B.
Mangalia
chosen
Mangalia is a Romanian Black Sea coastal resort town known for its ancient history, beaches, and spa tourism.
-
C.
Settara
Settara is a town and commune located in Jijel Province in northeastern Algeria.
-
D.
Aviapolis
Aviapolis is a major business and transportation district in Vantaa, Finland, centered around Helsinki Airport and known for its offices, logistics hubs, and commercial services.
-
E.
Gherla
Gherla is a town in northern Romania, historically known as Armenopolis, noted for its Armenian heritage and location in the Transylvanian region.
- 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_69ca84885e48819088a31b127cf44904 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cdec376cd48190990862c56c3a4dce |
completed | April 2, 2026, 4:10 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d2e6541e488190814e6395f219eb12 |
completed | April 5, 2026, 10:46 p.m. |
Created at: March 30, 2026, 9:08 p.m.