Triple
T13460524
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vasa (warship) |
E311349
|
entity |
| Predicate | hullPreservation |
P109591
|
FINISHED |
| Object | over 95 percent original |
—
|
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: over 95 percent original | Statement: [Vasa (warship), hullPreservation, over 95 percent original]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hullPreservation Context triple: [Vasa (warship), hullPreservation, over 95 percent original]
-
A.
hullConstruction
Indicates the process or activity of building, assembling, or forming the main body (hull) of a vessel or similar structure.
-
B.
hullNumber
Indicates the unique identifying number assigned to the hull of a ship or vessel.
-
C.
hullType
Indicates the specific structural design or configuration of an object's hull, typically classifying how its outer body or shell is shaped or constructed.
-
D.
shipwrecksRecoveredIn
Indicates the location or context in which shipwrecks have been found and recovered.
-
E.
wreckProtection
Indicates a relationship where one entity provides protection against damage, destruction, or wreckage to another entity.
- 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_69d806a938b8819097ec43a2229fc7f9 |
completed | April 9, 2026, 8:06 p.m. |
| NER | Named-entity recognition | batch_69dbaf0c177081909178dec61b09c278 |
completed | April 12, 2026, 2:41 p.m. |
| PD | Predicate disambiguation | batch_69d9a03dcd0c8190a8927eb4eaad1c45 |
completed | April 11, 2026, 1:13 a.m. |
| PDg | Predicate description generation | batch_69dadce235f88190a6433395d2969811 |
completed | April 11, 2026, 11:44 p.m. |
Created at: April 9, 2026, 9:41 p.m.