Triple
T10835009
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sulawesi region |
E255729
|
entity |
| Predicate | hasHighestPoint |
P210
|
FINISHED |
| Object |
Mount Rantemario
Mount Rantemario is a prominent mountain in Indonesia known as the highest peak on the island of Sulawesi.
|
E904877
|
NE FINISHED |
How this triple was built (4 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: Mount Rantemario | Statement: [Sulawesi region, hasHighestPoint, Mount Rantemario]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Rantemario Context triple: [Sulawesi region, hasHighestPoint, Mount Rantemario]
-
A.
Mount Ilandag
Mount Ilandag is a prominent volcanic mountain in the Nakhchivan region of Azerbaijan, noted for its distinctive shape and local legends.
-
B.
Mount Reimer
Mount Reimer is a mountain peak in the Sentinel Range of the Ellsworth Mountains in Western Antarctica.
-
C.
Mount Quarantania
Mount Quarantania is a cliffside mountain near Jericho traditionally identified as the site where Jesus fasted and was tempted by the devil according to the New Testament.
-
D.
Mount Majura
Mount Majura is a prominent hill in Canberra, Australia, known for its nature reserve, walking trails, and telecommunications facilities.
-
E.
Mount Farquhar
Mount Farquhar is a high, rugged peak in California’s Sierra Nevada, located along the remote Great Western Divide within Sequoia National Park.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg
Description generation
gpt-5.1
Instruction
Generate a one-sentence description of the target entity. You are given a context triple in the form (subject, predicate, object), where the object is the target entity. # Instructions Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. Avoid repeating the information from the triple, unless really essential. # Response Format Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: Mount Rantemario Triple: [Sulawesi region, hasHighestPoint, Mount Rantemario]
Generated description
Mount Rantemario is a prominent mountain in Indonesia known as the highest peak on the island of Sulawesi.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mount Rantemario Target entity description: Mount Rantemario is a prominent mountain in Indonesia known as the highest peak on the island of Sulawesi.
-
A.
Mount Ilandag
Mount Ilandag is a prominent volcanic mountain in the Nakhchivan region of Azerbaijan, noted for its distinctive shape and local legends.
-
B.
Mount Reimer
Mount Reimer is a mountain peak in the Sentinel Range of the Ellsworth Mountains in Western Antarctica.
-
C.
Mount Quarantania
Mount Quarantania is a cliffside mountain near Jericho traditionally identified as the site where Jesus fasted and was tempted by the devil according to the New Testament.
-
D.
Mount Majura
Mount Majura is a prominent hill in Canberra, Australia, known for its nature reserve, walking trails, and telecommunications facilities.
-
E.
Mount Farquhar
Mount Farquhar is a high, rugged peak in California’s Sierra Nevada, located along the remote Great Western Divide within Sequoia National Park.
- F. None of above. chosen
Provenance (5 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_69d6aa81a5d08190aa86689061d1ddd2 |
completed | April 8, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69d74425447081908fb51c7edf54af67 |
completed | April 9, 2026, 6:16 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69e3e6d27d8c8190b2c8ee9c54cf7fd1 |
completed | April 18, 2026, 8:17 p.m. |
| NEDg | Description generation | batch_69e3f01f9d048190b553184f0f6ce29c |
completed | April 18, 2026, 8:57 p.m. |
| NED2 | Entity disambiguation (via description) | batch_69e3f3fef9308190b0354ed436c32e4c |
completed | April 18, 2026, 9:13 p.m. |
Created at: April 8, 2026, 9:19 p.m.