Triple
T16348854
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nessus |
E397005
|
entity |
| Predicate | deception |
P7322
|
FINISHED |
| Object | claimed his blood would act as a love charm |
—
|
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: claimed his blood would act as a love charm | Statement: [Nessus, deception, claimed his blood would act as a love charm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: deception Context triple: [Nessus, deception, claimed his blood would act as a love charm]
-
A.
typeOfDeception
Indicates the specific kind or category of deceptive act that one entity employs toward another or in a given context.
-
B.
threatensDeceptionOf
Indicates that one entity poses or communicates a risk of deceiving or misleading another entity.
-
C.
tricked
chosen
Indicates that one entity intentionally deceived another into believing something false or acting under a false impression.
-
D.
allegedImpostor
Indicates that one entity is claimed or suspected to be fraudulently posing as another entity.
-
E.
betrayed
Indicates that one entity has broken the trust, loyalty, or confidence of another, typically by acting against their interests or revealing something meant to be kept secret.
- 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_69d87f26864c819088365ca381a003c2 |
completed | April 10, 2026, 4:40 a.m. |
| NER | Named-entity recognition | batch_69e2da10ef64819092633e8b32e98f5d |
completed | April 18, 2026, 1:10 a.m. |
| PD | Predicate disambiguation | batch_69e226f37ecc819082af58b29b4e39d1 |
completed | April 17, 2026, 12:26 p.m. |
Created at: April 10, 2026, 5:07 a.m.