Triple
T9773771
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Romney Marsh |
E237193
|
entity |
| Predicate | drainedBy |
P165
|
FINISHED |
| Object |
Rhee Wall
Rhee Wall is a medieval artificial watercourse and defensive earthwork in Kent, England, constructed to help drain and protect the low-lying Romney Marsh.
|
E819624
|
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: Rhee Wall | Statement: [Romney Marsh, drainedBy, Rhee Wall]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Rhee Wall Context triple: [Romney Marsh, drainedBy, Rhee Wall]
-
A.
In Sik Rhee
In Sik Rhee is a technology entrepreneur and venture capitalist best known as a co-founder of the cloud services company Loudcloud (later Opsware).
-
B.
Nakyung Park
Nakyung Park is a South Korean painter and artist best known publicly as the wife of American actor Wesley Snipes.
-
C.
Won-dong
Won-dong is a neighborhood (dong) within the city of Osan in Gyeonggi Province, South Korea.
-
D.
Hangang Park
Hangang Park is a large network of riverside parks in Seoul, South Korea, popular for recreation, festivals, and scenic views along the Han River.
-
E.
Kay Park
Kay Park is a public park in Kilmarnock, Scotland, known for its landscaped grounds, recreational spaces, and historical monuments.
- 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: Rhee Wall Triple: [Romney Marsh, drainedBy, Rhee Wall]
Generated description
Rhee Wall is a medieval artificial watercourse and defensive earthwork in Kent, England, constructed to help drain and protect the low-lying Romney Marsh.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Rhee Wall Target entity description: Rhee Wall is a medieval artificial watercourse and defensive earthwork in Kent, England, constructed to help drain and protect the low-lying Romney Marsh.
-
A.
In Sik Rhee
In Sik Rhee is a technology entrepreneur and venture capitalist best known as a co-founder of the cloud services company Loudcloud (later Opsware).
-
B.
Nakyung Park
Nakyung Park is a South Korean painter and artist best known publicly as the wife of American actor Wesley Snipes.
-
C.
Won-dong
Won-dong is a neighborhood (dong) within the city of Osan in Gyeonggi Province, South Korea.
-
D.
Hangang Park
Hangang Park is a large network of riverside parks in Seoul, South Korea, popular for recreation, festivals, and scenic views along the Han River.
-
E.
Kay Park
Kay Park is a public park in Kilmarnock, Scotland, known for its landscaped grounds, recreational spaces, and historical monuments.
- 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_69ca84d975a08190aab25b02a89bdab3 |
completed | March 30, 2026, 2:12 p.m. |
| NER | Named-entity recognition | batch_69cda0f6b8348190bd05b94519de9bc9 |
completed | April 1, 2026, 10:49 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69d1bd18542881908860f9e8e3927f23 |
completed | April 5, 2026, 1:38 a.m. |
| NEDg | Description generation | batch_69d1be312e208190985599c8447dc630 |
completed | April 5, 2026, 1:43 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69d1bea090b48190ae903036cc79dded |
completed | April 5, 2026, 1:45 a.m. |
Created at: March 30, 2026, 8:26 p.m.