Triple
T674928
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Saint Patrick |
E13056
|
entity |
| Predicate | patronage |
P2320
|
FINISHED |
| Object | Montserrat |
E17737
|
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: Montserrat | Statement: [Saint Patrick, patronage, Montserrat]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Montserrat Context triple: [Saint Patrick, patronage, Montserrat]
-
A.
Montserrat
chosen
Montserrat is a small Caribbean island and British Overseas Territory known for its volcanic activity and lush, mountainous landscape.
-
B.
Mount Aigaleo
Mount Aigaleo is a low mountain range in the Attica region of Greece, west of Athens, known for its historical and strategic significance overlooking the ancient battlefield of Salamis.
-
C.
Mount Pico
Mount Pico is a prominent stratovolcano on Pico Island in the Azores and the highest peak in Portugal.
-
D.
Mount Nivea
Mount Nivea is a prominent mountain peak that forms the highest point in the remote South Orkney Islands of the Southern Ocean.
-
E.
Nevis
Nevis is a small volcanic island in the Caribbean known for its lush landscapes, historic plantations, and tranquil beaches.
- 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_69a4933d3bf88190972041cd8cf143b9 |
completed | March 1, 2026, 7:27 p.m. |
| NER | Named-entity recognition | batch_69a4a0266e7c8190a94c4b4b761c59f4 |
completed | March 1, 2026, 8:23 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69a5c3a1b6588190b0c9215afb3a9200 |
completed | March 2, 2026, 5:06 p.m. |
Created at: March 1, 2026, 7:36 p.m.