Triple
T25361414
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Thorn Island |
E635975
|
entity |
| Predicate | hasNavigationRelevance |
P14917
|
FINISHED |
| Object | landmark in Milford Haven Waterway |
—
|
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: landmark in Milford Haven Waterway | Statement: [Thorn Island, hasNavigationRelevance, landmark in Milford Haven Waterway]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasNavigationRelevance Context triple: [Thorn Island, hasNavigationRelevance, landmark in Milford Haven Waterway]
-
A.
hasNavigationPurpose
Indicates that something exists or is designed specifically to serve a navigational function or goal.
-
B.
hasNavigationKnowledge
Indicates that an entity possesses information or expertise related to navigating or determining routes within an environment or system.
-
C.
hasNavigationUse
chosen
Indicates that something is used for navigation or serves a navigational function in relation to another entity.
-
D.
hasNavigationStatus
Indicates the current state or condition of an entity’s navigation, such as whether and how it is actively navigating.
-
E.
hasNavigationHazardRelevance
Indicates that something is relevant to, affected by, or poses a potential hazard to navigation.
- 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_69e75a9b7cf481909f2dcdfb37d95ca7 |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f650c70d7c819093d9a0f005f7c8d5 |
completed | May 2, 2026, 7:30 p.m. |
| PD | Predicate disambiguation | batch_69f64cab1f648190a2a9460690d18a37 |
completed | May 2, 2026, 7:12 p.m. |
Created at: April 21, 2026, 1:36 p.m.