Triple
T4958497
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tula |
E111344
|
entity |
| Predicate | hasTwinTown |
P919
|
FINISHED |
| Object | Akko |
E100560
|
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: Akko | Statement: [Tula, hasTwinTown, Akko]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Akko Context triple: [Tula, hasTwinTown, Akko]
-
A.
Akko
chosen
Akko is an ancient port city in northern Israel known for its well-preserved Crusader and Ottoman architecture and its designation as a UNESCO World Heritage Site.
-
B.
Tartus
Tartus is a major Syrian port city on the Mediterranean coast that hosts Russia’s only naval facility outside the former Soviet Union.
-
C.
Sidon
Sidon is an ancient Phoenician port city, located in present-day Lebanon, that was a major center of maritime trade and culture in the eastern Mediterranean.
-
D.
عكّا
عكّا هي مدينة تاريخية ساحلية في شمال فلسطين/إسرائيل تشتهر بقلعتها وأسوارها العثمانية ومينائها القديم وتراثها المتعدد الثقافات.
-
E.
Sidon Port
Sidon Port is the historic harbor of the ancient Phoenician city of Sidon in modern-day Lebanon, long known as a key Mediterranean maritime and trade hub.
- 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_69bd4418390c8190b7e9766a2512ce55 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd71d834c0819087f3faafdc9b4228 |
completed | March 20, 2026, 4:12 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be81e4ccc4819090223633fdb04eee |
completed | March 21, 2026, 11:32 a.m. |
Created at: March 20, 2026, 1:32 p.m.