Triple
T10378914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Towson |
E244580
|
entity |
| Predicate | nearbyWaterBody |
P1094
|
FINISHED |
| Object | Jones Falls |
E287715
|
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: Jones Falls | Statement: [Towson, nearbyWaterBody, Jones Falls]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Jones Falls Context triple: [Towson, nearbyWaterBody, Jones Falls]
-
A.
Jones Falls
chosen
Jones Falls is a significant stream in central Maryland that flows through Baltimore before joining the Patapsco River.
-
B.
Baltimore
Baltimore is a small coastal village in West Cork, Ireland, known for its fishing heritage, sailing, and as a gateway to nearby islands like Sherkin and Cape Clear.
-
C.
Baltimore
Baltimore is a major independent city and seaport in Maryland, United States, known for its historic harbor, diverse neighborhoods, and significant cultural and economic role in the Mid-Atlantic region.
-
D.
Mile Square City
Mile Square City is the popular nickname for Hoboken, New Jersey, referencing its compact size of roughly one square mile.
-
E.
Hat City
Hat City is the nickname of Danbury, Connecticut, reflecting its historic prominence as a major center of hat manufacturing in the United States.
- 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_69d381b3e328819094b23b8edcd29b5a |
completed | April 6, 2026, 9:49 a.m. |
| NER | Named-entity recognition | batch_69d4e98fead88190ace49f34b8a27c25 |
completed | April 7, 2026, 11:25 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d89f6254588190aa48e0092b0d5431 |
completed | April 10, 2026, 6:57 a.m. |
Created at: April 6, 2026, 12:03 p.m.