Triple
T1053753
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Komodo National Park |
E22755
|
entity |
| Predicate | containsIsland |
P970
|
FINISHED |
| Object | Komodo |
E27465
|
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: Komodo | Statement: [Komodo National Park, containsIsland, Komodo]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Komodo Context triple: [Komodo National Park, containsIsland, Komodo]
-
A.
Komodo
chosen
Komodo is an Indonesian island best known as the natural habitat of the Komodo dragon and a key part of Komodo National Park.
-
B.
Sumatran rhinoceros
The Sumatran rhinoceros is a critically endangered, small and hairy rhino species native to Southeast Asian forests, known as the most threatened of all living rhinoceroses.
-
C.
Dongo
Dongo is a small town on the northwestern shore of Lake Como in Lombardy, Italy, known for its role in the capture of Benito Mussolini at the end of World War II.
-
D.
Echidna
Echidna is a monstrous figure in Greek mythology, often called the "Mother of Monsters," who is typically depicted as half-woman and half-serpent.
-
E.
Derawali
Derawali is a regional dialect of the Saraiki language spoken primarily in and around the Dera Ghazi Khan and Dera Ismail Khan areas of Pakistan.
- 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_69a493da02e081908c13ff5e02a0fe7a |
completed | March 1, 2026, 7:30 p.m. |
| NER | Named-entity recognition | batch_69a4b8d669448190955507e2e4975b9f |
completed | March 1, 2026, 10:08 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69ac3bcf04448190af136ca4f037547b |
completed | March 7, 2026, 2:53 p.m. |
Created at: March 1, 2026, 7:42 p.m.