Triple
T9044892
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Surami Fortress |
E216729
|
entity |
| Predicate | nearbySettlement |
P350
|
FINISHED |
| Object | Surami |
E216725
|
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: Surami | Statement: [Surami Fortress, nearbySettlement, Surami]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Surami Context triple: [Surami Fortress, nearbySettlement, Surami]
-
A.
Surami
chosen
Surami is a historic town in central Georgia known for its medieval fortress and role as a transport and resort hub in the Shida Kartli region.
-
B.
Rotima
Rotima is a small settlement located on the island of Nonouti in the Republic of Kiribati.
-
C.
Lemi
Lemi is a small rural municipality in southeastern Finland known for its lakes, forests, and traditional Karelian culture.
-
D.
Seia
Seia is a municipality and town in central Portugal known for its proximity to the Serra da Estrela mountains and natural park.
-
E.
Rukmi
Rukmi is a character in Hindu mythology known as the proud and antagonistic brother of Rukmini, who opposed her marriage to Krishna.
- 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_69ca83d22d488190adbce5e020e9cd1d |
completed | March 30, 2026, 2:08 p.m. |
| NER | Named-entity recognition | batch_69cc6b148b188190814d64acae493634 |
completed | April 1, 2026, 12:47 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d0177fb9108190846fe872bb003b08 |
completed | April 3, 2026, 7:39 p.m. |
Created at: March 30, 2026, 7:09 p.m.