Triple
T588830
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tutuila |
E17220
|
entity |
| Predicate | hasRoadNetwork |
P3293
|
FINISHED |
| Object | primary highway along south coast |
—
|
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: primary highway along south coast | Statement: [Tutuila, hasRoadNetwork, primary highway along south coast]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRoadNetwork Context triple: [Tutuila, hasRoadNetwork, primary highway along south coast]
-
A.
isPublicRoadNetwork
Indicates that a given road network is officially designated for public use and accessible to the general public for transportation.
-
B.
transportNetwork
Indicates a relationship where infrastructure or services enable the movement of people or goods between different locations.
-
C.
streetNetwork
Indicates the layout and connectivity relationships among streets within a geographic area, including how roads intersect, link, and form a navigable network.
-
D.
roadSystem
chosen
Indicates a relationship where multiple roads are organized and connected as part of a larger, integrated transportation network or infrastructure.
-
E.
hasMajorHighway
Indicates that a location or area is served by or directly connected to a major highway route.
- 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_69a49379d09c8190ac7e00b24e2810b1 |
completed | March 1, 2026, 7:28 p.m. |
| NER | Named-entity recognition | batch_69a49b9d1e68819096a9b5e7b2e83d6e |
completed | March 1, 2026, 8:03 p.m. |
| PD | Predicate disambiguation | batch_69a494ca68448190a516b9c3525d8916 |
completed | March 1, 2026, 7:34 p.m. |
Created at: March 1, 2026, 7:33 p.m.