Triple
T29432117
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Seldon Vault |
E746458
|
entity |
| Predicate | concealment |
P177563
|
FINISHED |
| Object | hidden location on Terminus |
—
|
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: hidden location on Terminus | Statement: [Seldon Vault, concealment, hidden location on Terminus]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: concealment Context triple: [Seldon Vault, concealment, hidden location on Terminus]
-
A.
concealmentType
Indicates the specific manner or method by which something is hidden, obscured, or kept from detection.
-
B.
concealability
Indicates the degree to which something can be hidden or kept from being noticed or discovered.
-
C.
riskConcealment
Indicates that one party hides, downplays, or fails to disclose potential dangers, losses, or adverse outcomes associated with something to another party.
-
D.
secretive
Indicates that an entity deliberately withholds information or conceals its thoughts, actions, or intentions from others.
-
E.
triesToConcealCrimeFrom
Indicates an attempt by one entity to hide, obscure, or prevent another entity from discovering or becoming aware of a crime.
- F. None of above. chosen
Provenance (4 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_69f0a7a06e0081908add494075912eb4 |
completed | April 28, 2026, 12:27 p.m. |
| NER | Named-entity recognition | batch_69f7009d39508190af7301f824615e88 |
completed | May 3, 2026, 8 a.m. |
| PD | Predicate disambiguation | batch_69f6fc53f4f881908dcc698687bbb64d |
completed | May 3, 2026, 7:42 a.m. |
| PDg | Predicate description generation | batch_69f6ffb7554881908993d6d2ffbcf8f5 |
completed | May 3, 2026, 7:56 a.m. |
Created at: April 28, 2026, 3:14 p.m.