Triple
T12705631
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lighthouse Reef (dive site) |
E303576
|
entity |
| Predicate | typicalVisibility |
P106282
|
FINISHED |
| Object | good |
—
|
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: good | Statement: [Lighthouse Reef (dive site), typicalVisibility, good]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalVisibility Context triple: [Lighthouse Reef (dive site), typicalVisibility, good]
-
A.
typicalConsistency
Indicates that one entity characteristically maintains a regular or expected level of consistency in relation to another entity or context.
-
B.
typicalIn
Indicates that something commonly occurs, appears, or is found within a given context, category, or environment.
-
C.
typicalScope
Indicates the usual or expected range, extent, or domain within which something normally applies, operates, or is relevant.
-
D.
typicalVisitType
Indicates the usual or most common category of visit associated with an entity or event.
-
E.
typicalAlignment
Indicates the usual or most common way in which two entities are positioned, oriented, or arranged relative to each other.
- 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_69d7bdef90d48190b46b88270e780946 |
completed | April 9, 2026, 2:55 p.m. |
| NER | Named-entity recognition | batch_69d961f1adec8190a53c80e9556b3fe0 |
completed | April 10, 2026, 8:47 p.m. |
| PD | Predicate disambiguation | batch_69d960c088dc8190b0e63312c54e4c6c |
completed | April 10, 2026, 8:42 p.m. |
| PDg | Predicate description generation | batch_69d961acadb8819098de743bc951fedb |
completed | April 10, 2026, 8:46 p.m. |
Created at: April 9, 2026, 5:23 p.m.