Triple
T3694921
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Salisbury, Connecticut |
E78433
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Mount Riga
Mount Riga is a scenic, forested highland area in northwestern Connecticut known for its hiking trails, lakes, and historic iron industry sites.
|
E381350
|
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 Riga | Statement: [Salisbury, Connecticut, contains, Mount Riga]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mount Riga Context triple: [Salisbury, Connecticut, contains, Mount Riga]
-
A.
Maritsa Peak
Maritsa Peak is a mountain summit whose slopes give rise to the Maritsa River, one of the major rivers of the Balkans.
-
B.
Mount Egon
Mount Egon is an active stratovolcano located on the island of Flores in Indonesia, known for its periodic eruptions and geothermal activity.
-
C.
Mount Oros
Mount Oros is the highest mountain on the Greek island of Aegina, known for its panoramic views and historical religious sites.
-
D.
Mount Narodnaya
Mount Narodnaya is a prominent peak in Russia known as the tallest mountain in the Ural range, marking the natural boundary between Europe and Asia.
-
E.
Mount Skoumbarda
Mount Skoumbarda is the highest peak on the Greek island of Leros in the southeastern Aegean Sea.
- 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 Riga Triple: [Salisbury, Connecticut, contains, Mount Riga]
Generated description
Mount Riga is a scenic, forested highland area in northwestern Connecticut known for its hiking trails, lakes, and historic iron industry sites.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mount Riga Target entity description: Mount Riga is a scenic, forested highland area in northwestern Connecticut known for its hiking trails, lakes, and historic iron industry sites.
-
A.
Maritsa Peak
Maritsa Peak is a mountain summit whose slopes give rise to the Maritsa River, one of the major rivers of the Balkans.
-
B.
Mount Egon
Mount Egon is an active stratovolcano located on the island of Flores in Indonesia, known for its periodic eruptions and geothermal activity.
-
C.
Mount Oros
Mount Oros is the highest mountain on the Greek island of Aegina, known for its panoramic views and historical religious sites.
-
D.
Mount Narodnaya
Mount Narodnaya is a prominent peak in Russia known as the tallest mountain in the Ural range, marking the natural boundary between Europe and Asia.
-
E.
Mount Skoumbarda
Mount Skoumbarda is the highest peak on the Greek island of Leros in the southeastern Aegean Sea.
- 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_69ad85e3b1888190abc983e06968696d |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc4eafd348190986f69aee787fd8f |
completed | March 8, 2026, 6:50 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b4cdeee0488190b59e24f8ad48ad5e |
completed | March 14, 2026, 2:54 a.m. |
| NEDg | Description generation | batch_69b4cf08b5688190867da982cc464d5a |
completed | March 14, 2026, 2:59 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b4cf6c4e5c8190bee35fc33d707823 |
completed | March 14, 2026, 3:01 a.m. |
Created at: March 8, 2026, 3:26 p.m.