Triple
T8430505
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Rose DeWitt Bukater |
E199102
|
entity |
| Predicate | poseDescription |
P42040
|
FINISHED |
| Object | wearing only the Heart of the Ocean |
—
|
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: wearing only the Heart of the Ocean | Statement: [Rose DeWitt Bukater, poseDescription, wearing only the Heart of the Ocean]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: poseDescription Context triple: [Rose DeWitt Bukater, poseDescription, wearing only the Heart of the Ocean]
-
A.
describesPosture
chosen
Indicates that one entity specifies or characterizes the bodily position or stance (posture) of another entity.
-
B.
describes
Indicates that one entity provides an explanation, representation, or account of another entity or concept.
-
C.
designDescription
Indicates that an entity has a textual explanation or summary of its design, structure, or intended configuration.
-
D.
describedIn
Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
-
E.
targetDescription
Indicates that an entity provides a textual explanation or characterization of a specified target entity or concept.
- 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_69ca8313c99081909a5c6d83b91de5b3 |
completed | March 30, 2026, 2:05 p.m. |
| NER | Named-entity recognition | batch_69cbe30fba4081908bfdef3faf5baceb |
completed | March 31, 2026, 3:06 p.m. |
| PD | Predicate disambiguation | batch_69cbd0ec200c8190b0299e2b0b4bdcc2 |
completed | March 31, 2026, 1:49 p.m. |
Created at: March 30, 2026, 6:07 p.m.