Triple
T36198024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Michael Gregson |
E1047180
|
entity |
| Predicate | keepsRelationshipSecretFrom |
P22701
|
FINISHED |
| Object | Crawley family |
—
|
NE NERFINISHED |
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: Crawley family | Statement: [Michael Gregson, keepsRelationshipSecretFrom, Crawley family]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: keepsRelationshipSecretFrom Context triple: [Michael Gregson, keepsRelationshipSecretFrom, Crawley family]
-
A.
keepsSecretAbout
chosen
Indicates that one entity intentionally withholds or conceals information regarding another specified entity or topic from others.
-
B.
familySecretInvolves
Indicates that a particular family secret concerns, affects, or is about the specified entity or entities.
-
C.
keptPastSecretFrom
Indicates that one entity intentionally withheld or concealed information from another entity in the past.
-
D.
secretlyPreserves
Indicates that one entity preserves or maintains something related to another entity in a concealed or undisclosed manner.
-
E.
secretlyIs
Indicates that one entity possesses a hidden or undisclosed identity, role, or attribute in relation 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_69f76e414bdc8190996f15a544220a3d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7b69b333081909cadbed3fcb8ecf5 |
completed | May 3, 2026, 8:56 p.m. |
| PD | Predicate disambiguation | batch_69f7b4c2a5f8819094ad4621d7b97e0c |
completed | May 3, 2026, 8:49 p.m. |
Created at: May 3, 2026, 4:08 p.m.