Triple
T36838626
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Penobscot Indian Island Reservation |
E910342
|
entity |
| Predicate | riverIslandOn |
P156002
|
FINISHED |
| Object | Penobscot River |
—
|
NE NERFINISHED |
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: Penobscot River | Statement: [Penobscot Indian Island Reservation, riverIslandOn, Penobscot River]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: riverIslandOn Context triple: [Penobscot Indian Island Reservation, riverIslandOn, Penobscot River]
-
A.
riverIslandSettlement
Indicates a settlement that is located on an island within a river.
-
B.
isOnRiverIsland
chosen
Indicates that one entity (typically a place or structure) is located on an island situated within a river.
-
C.
riverIslandArchipelagoNearby
Indicates that a river island is located close to or within the vicinity of an archipelago.
-
D.
islandOf
Indicates that one place is an island belonging to, located within, or geographically associated with another specified area or body of land/water.
-
E.
locatedOnIslandOfCountry
Indicates that something is situated on an island that belongs to, or is part of, a specified country.
- 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_69f76e7f65a881908651b702da592b6d |
completed | May 3, 2026, 3:49 p.m. |
| NER | Named-entity recognition | batch_69fa0a7b00948190a257273d9968c5d7 |
completed | May 5, 2026, 3:19 p.m. |
| PD | Predicate disambiguation | batch_69f9fec9c9488190ae2a349651a02782 |
completed | May 5, 2026, 2:29 p.m. |
Created at: May 3, 2026, 4:13 p.m.