Triple
T14905954
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Hudson Falls, New York |
E360130
|
entity |
| Predicate | previousName |
P65
|
FINISHED |
| Object |
Sandy Hill
Sandy Hill is the former name of the village now known as Hudson Falls in Washington County, New York.
|
E1128324
|
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: Sandy Hill | Statement: [Hudson Falls, New York, previousName, Sandy Hill]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Sandy Hill Context triple: [Hudson Falls, New York, previousName, Sandy Hill]
-
A.
Sandy Hill
Sandy Hill is a historic, centrally located Ottawa neighbourhood known for its mix of embassies, university buildings, and diverse residential areas.
-
B.
Saddle Hill
Saddle Hill is the English meaning of "Cerro de la Silla," a famous saddle-shaped mountain and landmark overlooking Monterrey, Mexico.
-
C.
Brewster Hill
Brewster Hill is a small residential hamlet within the Town of Southeast in Putnam County, New York.
-
D.
Arbour Hill
Arbour Hill is a historic inner-city area of Dublin, Ireland, best known for its military barracks and cemetery containing the graves of leaders of the 1916 Easter Rising.
-
E.
Shippea Hill
Shippea Hill is a small, rural railway station in Cambridgeshire, England, known for its very low passenger usage and location on a remote stretch of fenland.
- 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: Sandy Hill Triple: [Hudson Falls, New York, previousName, Sandy Hill]
Generated description
Sandy Hill is the former name of the village now known as Hudson Falls in Washington County, New York.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Sandy Hill Target entity description: Sandy Hill is the former name of the village now known as Hudson Falls in Washington County, New York.
-
A.
Sandy Hill
Sandy Hill is a historic, centrally located Ottawa neighbourhood known for its mix of embassies, university buildings, and diverse residential areas.
-
B.
Saddle Hill
Saddle Hill is the English meaning of "Cerro de la Silla," a famous saddle-shaped mountain and landmark overlooking Monterrey, Mexico.
-
C.
Brewster Hill
Brewster Hill is a small residential hamlet within the Town of Southeast in Putnam County, New York.
-
D.
Arbour Hill
Arbour Hill is a historic inner-city area of Dublin, Ireland, best known for its military barracks and cemetery containing the graves of leaders of the 1916 Easter Rising.
-
E.
Shippea Hill
Shippea Hill is a small, rural railway station in Cambridgeshire, England, known for its very low passenger usage and location on a remote stretch of fenland.
- 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_69d827980cbc8190a0c569ae3940a1d9 |
completed | April 9, 2026, 10:26 p.m. |
| NER | Named-entity recognition | batch_69ded60cd5588190b1efecc2b220da69 |
completed | April 15, 2026, 12:04 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69fe7e84d9e481908edd6e3e5e14da54 |
completed | May 9, 2026, 12:23 a.m. |
| NEDg | Description generation | batch_69fe7f8cdc8c81908c961ffa83cbd19e |
completed | May 9, 2026, 12:27 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69fe801d6b048190a7c7e50ad53b1260 |
completed | May 9, 2026, 12:30 a.m. |
Created at: April 10, 2026, 2:12 a.m.