Triple
T6182215
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Marine Security Guard |
E137968
|
entity |
| Predicate | tourLength |
P69534
|
FINISHED |
| Object | typically 12 to 36 months depending on assignment |
—
|
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: typically 12 to 36 months depending on assignment | Statement: [Marine Security Guard, tourLength, typically 12 to 36 months depending on assignment]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: tourLength Context triple: [Marine Security Guard, tourLength, typically 12 to 36 months depending on assignment]
-
A.
totalRouteLength
Indicates the overall distance or length of an entire route when all its segments are combined.
-
B.
trailDistanceApprox
Indicates that the distance along a trail between two locations is approximately a specified value, allowing for some margin of error.
-
C.
trailLengthApprox
Indicates an approximate measurement of the total length of a trail.
-
D.
touristCorridorLength
Indicates the measured length or extent of a designated tourist corridor or route.
-
E.
distanceTraveled
Indicates the total length of the path an entity has moved over a period of time or between two points.
- F. None of above. chosen
Provenance (4 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_69c008a80f748190ba3d07ffc81acb29 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c060ff9e488190b79957dfaefcca54 |
completed | March 22, 2026, 9:37 p.m. |
| PD | Predicate disambiguation | batch_69c055fa0a808190bda37832e3ac150c |
completed | March 22, 2026, 8:50 p.m. |
| PDg | Predicate description generation | batch_69c056c87340819088003f427706ebf8 |
completed | March 22, 2026, 8:53 p.m. |
Created at: March 22, 2026, 4:19 p.m.