Triple
T23931507
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Greenwich, Massachusetts |
E602509
|
entity |
| Predicate | remnantsVisibleAt |
P35040
|
FINISHED |
| Object | Quabbin Reservoir drawdown periods |
—
|
LITERAL 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: Quabbin Reservoir drawdown periods | Statement: [Greenwich, Massachusetts, remnantsVisibleAt, Quabbin Reservoir drawdown periods]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: remnantsVisibleAt Context triple: [Greenwich, Massachusetts, remnantsVisibleAt, Quabbin Reservoir drawdown periods]
-
A.
visibleRemains
chosen
Indicates that some physical remnants of an entity or event can still be seen or visually detected.
-
B.
remnantDetected
Indicates that a remaining trace or leftover of a prior entity, event, or process has been identified.
-
C.
remnantsInclude
Indicates that the remaining parts or leftovers of one entity contain or consist of another entity.
-
D.
remnants
Indicates that parts or traces of something remain after the main portion has been removed, used, or destroyed.
-
E.
remnantType
Indicates the specific kind or category of remnant that results from or is associated with an entity or process.
- F. None of above.
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_69e2953b928c819095395fa87baca583 |
completed | April 17, 2026, 8:16 p.m. |
| NER | Named-entity recognition | batch_69f1cf9c223881908e5fa4b5564848e6 |
completed | April 29, 2026, 9:30 a.m. |
| PD | Predicate disambiguation | batch_69f16151ebdc819086e9e1d7cc1f4f3c |
completed | April 29, 2026, 1:39 a.m. |
Created at: April 17, 2026, 8:58 p.m.