Triple
T5175982
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Deianira |
E116798
|
entity |
| Predicate | actuallyPropertyOfObject |
P23698
|
FINISHED |
| Object | blood of Nessus as poison |
—
|
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: blood of Nessus as poison | Statement: [Deianira, actuallyPropertyOfObject, blood of Nessus as poison]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: actuallyPropertyOfObject Context triple: [Deianira, actuallyPropertyOfObject, blood of Nessus as poison]
-
A.
identifiesPropertyOf
Indicates that one entity specifies or denotes a particular property or attribute belonging to another entity.
-
B.
haveProperty
chosen
Indicates that an entity possesses, exhibits, or is characterized by a particular property or attribute.
-
C.
ownedProperty
Indicates that one entity possesses legal ownership or control over another entity as property.
-
D.
isContributingPropertyTo
Indicates that one property plays a role in producing, influencing, or determining another property or overall outcome.
-
E.
protégéOf
Indicates that one entity is mentored, trained, or guided in their development by another, more experienced 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_69bd446140f08190becb93c61158f27f |
completed | March 20, 2026, 12:58 p.m. |
| NER | Named-entity recognition | batch_69bd797349008190b87ad9d0d3eb667f |
completed | March 20, 2026, 4:44 p.m. |
| PD | Predicate disambiguation | batch_69bd77b529948190b86671ebe43f4734 |
completed | March 20, 2026, 4:37 p.m. |
Created at: March 20, 2026, 1:45 p.m.