Triple
T35966667
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | SS City of Detroit III wreck |
E1040159
|
entity |
| Predicate | protectionNeed |
P15826
|
FINISHED |
| Object | underwater cultural heritage preservation |
—
|
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: underwater cultural heritage preservation | Statement: [SS City of Detroit III wreck, protectionNeed, underwater cultural heritage preservation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protectionNeed Context triple: [SS City of Detroit III wreck, protectionNeed, underwater cultural heritage preservation]
-
A.
providesProtectionIn
Indicates that one entity offers protection or safeguarding to another entity within a specified context, location, or situation.
-
B.
protectionMeasures
Indicates actions or safeguards implemented to prevent harm, damage, or risk to someone or something.
-
C.
protectionType
chosen
Indicates the kind or method of protection that is applied to or associated with an entity.
-
D.
believedToProtect
Indicates that one entity is thought or assumed to provide protection or defense for another entity.
-
E.
providesProtectionAgainst
Indicates that one entity serves to guard, shield, or defend another entity from a specified harm, threat, or adverse effect.
- 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_69f76e26b21081909fd9ffb3aff6c77a |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_69f7acaec1508190a38f2ac9cc5383e7 |
completed | May 3, 2026, 8:14 p.m. |
| PD | Predicate disambiguation | batch_69f7ab75387c819091afc3c2128eb903 |
completed | May 3, 2026, 8:09 p.m. |
Created at: May 3, 2026, 4:07 p.m.