Triple
T38009973
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mr Tulkinghorn |
E948337
|
entity |
| Predicate | secretKnowledgeAbout |
P71015
|
FINISHED |
| Object | Lady Dedlock's past |
—
|
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: Lady Dedlock's past | Statement: [Mr Tulkinghorn, secretKnowledgeAbout, Lady Dedlock's past]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: secretKnowledgeAbout Context triple: [Mr Tulkinghorn, secretKnowledgeAbout, Lady Dedlock's past]
-
A.
secretlyInformed
Indicates that one entity provided information to another in a concealed or confidential manner, without the knowledge of others.
-
B.
revealedSecretOf
Indicates that one entity has disclosed or exposed confidential or previously unknown information belonging to another entity.
-
C.
knowsSecret
chosen
Indicates that one entity is aware of confidential or hidden information about another entity or situation.
-
D.
secretDetail
Indicates that one entity reveals or contains confidential or hidden information about another entity or situation.
-
E.
secretRevealed
Indicates that previously hidden or confidential information has been disclosed to one or more parties.
- 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_69f76efb4b10819092c8c2ba28ac06a8 |
completed | May 3, 2026, 3:51 p.m. |
| NER | Named-entity recognition | batch_69fbc995dc2481908b3bd4217f8101e7 |
completed | May 6, 2026, 11:07 p.m. |
| PD | Predicate disambiguation | batch_69fbc8ee04f08190977b7ad70fc85896 |
completed | May 6, 2026, 11:04 p.m. |
Created at: May 3, 2026, 4:20 p.m.