Triple
T35577298
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Blue Holes dive site |
E1028114
|
entity |
| Predicate | typicalStartingDepth |
P85156
|
FINISHED |
| Object | reef top around 5 to 10 meters |
—
|
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: reef top around 5 to 10 meters | Statement: [Blue Holes dive site, typicalStartingDepth, reef top around 5 to 10 meters]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typicalStartingDepth Context triple: [Blue Holes dive site, typicalStartingDepth, reef top around 5 to 10 meters]
-
A.
typicalAnalysisDepth
Indicates the usual or characteristic level of detail or depth at which an analysis is performed or interpreted between entities.
-
B.
typicalFormationDepth
Indicates the usual or characteristic depth at which something is formed or occurs within a medium or environment.
-
C.
typicalStartElevation
chosen
Indicates the usual or characteristic elevation at which something (such as a route, feature, or activity) typically begins.
-
D.
typicalHighestLevel
Indicates the usual or most common maximum level or degree that something typically reaches within a given context.
-
E.
typicalDifficulty
Indicates the usual or characteristic level of difficulty associated with performing an action or achieving a particular outcome.
- 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_69f76e0386688190b931bacdc145938c |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a037c8d06cc8190ab6a5e18d9d2571e |
completed | May 12, 2026, 7:16 p.m. |
| PD | Predicate disambiguation | batch_6a037a04d8348190a4819666eab42c9b |
completed | May 12, 2026, 7:05 p.m. |
Created at: May 3, 2026, 4:04 p.m.