Triple
T4859015
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Brookhaven |
E108608
|
entity |
| Predicate | contains |
P35
|
FINISHED |
| Object |
Mastic
Mastic is a hamlet on Long Island in Suffolk County, New York, known as a residential community near the south shore.
|
E474765
|
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: Mastic | Statement: [Brookhaven, contains, Mastic]
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Mastic Context triple: [Brookhaven, contains, Mastic]
-
A.
Mastic–Shirley
Mastic–Shirley is a Long Island Rail Road station in Suffolk County, New York, serving the neighboring communities of Mastic and Shirley.
-
B.
Shellac
Shellac is an American minimalist noise rock band known for its abrasive sound, precise rhythms, and the distinctive production style of guitarist and recording engineer Steve Albini.
-
C.
Oglio
The Oglio is a river in northern Italy that flows through Lombardy and is one of the main tributaries of the Po River.
-
D.
Comino
Comino is a small, sparsely populated Maltese island in the Mediterranean Sea, best known for its clear waters and the popular Blue Lagoon.
-
E.
Tartegnin
Tartegnin is a small wine-producing municipality in the canton of Vaud in western Switzerland, situated above Lake Geneva in the La Côte region.
- 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: Mastic Triple: [Brookhaven, contains, Mastic]
Generated description
Mastic is a hamlet on Long Island in Suffolk County, New York, known as a residential community near the south shore.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Mastic Target entity description: Mastic is a hamlet on Long Island in Suffolk County, New York, known as a residential community near the south shore.
-
A.
Mastic–Shirley
Mastic–Shirley is a Long Island Rail Road station in Suffolk County, New York, serving the neighboring communities of Mastic and Shirley.
-
B.
Shellac
Shellac is an American minimalist noise rock band known for its abrasive sound, precise rhythms, and the distinctive production style of guitarist and recording engineer Steve Albini.
-
C.
Oglio
The Oglio is a river in northern Italy that flows through Lombardy and is one of the main tributaries of the Po River.
-
D.
Comino
Comino is a small, sparsely populated Maltese island in the Mediterranean Sea, best known for its clear waters and the popular Blue Lagoon.
-
E.
Tartegnin
Tartegnin is a small wine-producing municipality in the canton of Vaud in western Switzerland, situated above Lake Geneva in the La Côte region.
- 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_69bd440b965081908b0557721cae6338 |
completed | March 20, 2026, 12:56 p.m. |
| NER | Named-entity recognition | batch_69bd6d5c92148190a314707bdd3ff30f |
completed | March 20, 2026, 3:53 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_69be5cf05d7c8190ac6e1b9e93b5256f |
completed | March 21, 2026, 8:55 a.m. |
| NEDg | Description generation | batch_69be5f98d4d481908eedf03569d38642 |
completed | March 21, 2026, 9:06 a.m. |
| NED2 | Entity disambiguation (via description) | batch_69be6044d31081908384ed9da8c6b707 |
completed | March 21, 2026, 9:09 a.m. |
Created at: March 20, 2026, 1:26 p.m.