Triple
T4478897
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | King Island |
E100078
|
entity |
| Predicate | hasSettlement |
P1068
|
FINISHED |
| Object |
Grassy
Grassy is a small coastal township on King Island in Tasmania, Australia, historically associated with mining and local fishing activities.
|
E441865
|
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: Grassy | Statement: [King Island, hasSettlement, Grassy]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Grassy Context triple: [King Island, hasSettlement, Grassy]
-
A.
Boggy
Boggy was the original name of the city now known as Niceville in Florida.
-
B.
Grass
Grass is a 1925 silent documentary film that follows the arduous seasonal migration of the Bakhtiari tribe in Iran, co-directed by Merian C. Cooper and Ernest B. Schoedsack.
-
C.
Meadows
Meadows is a surname most prominently associated with Mark Meadows, a former White House Chief of Staff and U.S. congressman.
-
D.
Eyebroughy
Eyebroughy is a small rocky islet in the Firth of Forth, Scotland, known as a protected bird sanctuary and notable feature of the coastal landscape near North Berwick.
-
E.
Vignely
Vignely is a small French commune located in the Seine-et-Marne department in the Île-de-France region in north-central France.
- 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: Grassy Triple: [King Island, hasSettlement, Grassy]
Generated description
Grassy is a small coastal township on King Island in Tasmania, Australia, historically associated with mining and local fishing activities.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Grassy Target entity description: Grassy is a small coastal township on King Island in Tasmania, Australia, historically associated with mining and local fishing activities.
-
A.
Boggy
Boggy was the original name of the city now known as Niceville in Florida.
-
B.
Grass
Grass is a 1925 silent documentary film that follows the arduous seasonal migration of the Bakhtiari tribe in Iran, co-directed by Merian C. Cooper and Ernest B. Schoedsack.
-
C.
Meadows
Meadows is a surname most prominently associated with Mark Meadows, a former White House Chief of Staff and U.S. congressman.
-
D.
Eyebroughy
Eyebroughy is a small rocky islet in the Firth of Forth, Scotland, known as a protected bird sanctuary and notable feature of the coastal landscape near North Berwick.
-
E.
Vignely
Vignely is a small French commune located in the Seine-et-Marne department in the Île-de-France region in north-central France.
- 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_69b34553cbe48190afa8ac1cac285b86 |
completed | March 12, 2026, 10:59 p.m. |
| NER | Named-entity recognition | batch_69b356db0a008190ad39b68efc095b8d |
completed | March 13, 2026, 12:14 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69b62888ea508190a052c0b2edee7fca |
completed | March 15, 2026, 3:33 a.m. |
| NEDg | Description generation | batch_69b6295721d881908d49ce1944e0ed17 |
completed | March 15, 2026, 3:36 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69b62a3e9d1c8190a613726d45622406 |
completed | March 15, 2026, 3:40 a.m. |
Created at: March 12, 2026, 11:35 p.m.