Triple
T38342896
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | South Carolina Aquarium |
E1041454
|
entity |
| Predicate | Great Ocean TankCapacity |
P190444
|
FINISHED |
| Object | approximately 385,000 gallons |
—
|
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: approximately 385,000 gallons | Statement: [South Carolina Aquarium, Great Ocean TankCapacity, approximately 385,000 gallons]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: Great Ocean TankCapacity Context triple: [South Carolina Aquarium, Great Ocean TankCapacity, approximately 385,000 gallons]
-
A.
hasOcean
Indicates that a geographic region, country, or landmass is bordered by or directly adjacent to a particular ocean.
-
B.
Waterline
Indicates the level or line on an object or surface that marks where water reaches or has reached.
-
C.
submarineCapacity
Indicates the maximum number of people or amount of cargo that a submarine is designed or allowed to carry.
-
D.
lifeboatCapacity
Indicates the maximum number of people or load that a lifeboat is designed and certified to safely carry.
-
E.
mainTankCapacity
Indicates the maximum volume of fuel or liquid that the primary tank is designed to hold.
- 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_69f76e2ad95481908c920c0e5c1c3e26 |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69fcc7a4d7f881908b43b960911b81e9 |
completed | May 7, 2026, 5:11 p.m. |
| PD | Predicate disambiguation | batch_69fcc589720c819089c8f500fea3c86a |
completed | May 7, 2026, 5:02 p.m. |
| PDg | Predicate description generation | batch_69fcc7a42f68819081d6ec8bb6b53438 |
completed | May 7, 2026, 5:11 p.m. |
Created at: May 3, 2026, 4:30 p.m.