Triple
T17720979
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Montserrat |
E442335
|
entity |
| Predicate | locationRelative |
P7317
|
FINISHED |
| Object | south-east of Puerto Rico |
—
|
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: south-east of Puerto Rico | Statement: [Montserrat, locationRelative, south-east of Puerto Rico]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: locationRelative Context triple: [Montserrat, locationRelative, south-east of Puerto Rico]
-
A.
relativePosition
Indicates the spatial relationship of one entity’s location with respect to another entity’s position.
-
B.
hasRelativeLocation
chosen
Indicates that one entity is positioned in space in relation to another entity’s location.
-
C.
locationRelativeToIP
Indicates a spatial or geographic relationship between an entity and a given IP address’s inferred location.
-
D.
depthRelativeDescription
Indicates a description of how deep one entity is in relation to another reference point or entity.
-
E.
relativePositioning
Indicates how one entity is spatially arranged or located in relation to another entity.
- 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_69d8b9ec79688190b86bdcef85a7b3aa |
completed | April 10, 2026, 8:50 a.m. |
| NER | Named-entity recognition | batch_69e4748520a881908dc3446d33236ff7 |
completed | April 19, 2026, 6:21 a.m. |
| PD | Predicate disambiguation | batch_69e3cde601d4819097903f471f1fe99a |
completed | April 18, 2026, 6:31 p.m. |
Created at: April 10, 2026, 10:07 a.m.