Triple
T20980052
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Captain Frederick Wentworth |
E516732
|
entity |
| Predicate | letterQuote |
P78667
|
FINISHED |
| Object | You pierce my soul. I am half agony, half hope. |
—
|
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: You pierce my soul. I am half agony, half hope. | Statement: [Captain Frederick Wentworth, letterQuote, You pierce my soul. I am half agony, half hope.]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: letterQuote Context triple: [Captain Frederick Wentworth, letterQuote, You pierce my soul. I am half agony, half hope.]
-
A.
quotationText
chosen
Indicates that the associated text is the exact content of a quotation made or referenced in the relationship.
-
B.
quoteType
Indicates the specific category or classification of a quotation, such as its style, purpose, or contextual role in discourse.
-
C.
quoteLanguage
Indicates that a quoted text is expressed in a particular language.
-
D.
notableQuote
Indicates that one entity is a significant or well-known quotation attributed to, recorded by, or strongly associated with another entity.
-
E.
quoteProvision
Indicates that one entity supplies or presents a quotation or price estimate to another entity.
- 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_69e0b4ffac148190bbade9f0eceb660b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fbdd89f48190b58c67cc1f7968c0 |
completed | April 21, 2026, 4:23 a.m. |
| PD | Predicate disambiguation | batch_69e5dbe6976081908abd4e9c8734bae9 |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:47 p.m.