Triple
T35977671
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Snowbell |
E1040467
|
entity |
| Predicate | laterAttitudeTowardStuart |
P202517
|
FINISHED |
| Object | protective |
—
|
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: protective | Statement: [Snowbell, laterAttitudeTowardStuart, protective]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laterAttitudeTowardStuart Context triple: [Snowbell, laterAttitudeTowardStuart, protective]
-
A.
laterAttitudeTowardAllison
Indicates a subject’s attitude or feelings toward Allison at a subsequent time relative to some earlier reference point.
-
B.
attitudeTowardReform
Indicates an entity’s stance, opinion, or disposition regarding a proposed or ongoing reform.
-
C.
attitudeTowardEmpire
Indicates the stance, opinion, or disposition an entity holds toward an empire or imperial system.
-
D.
laterAttitudeTowardJane
Indicates a subject’s attitude or feelings toward Jane at a later point in time relative to some earlier reference time.
-
E.
laterStance
Indicates that one stance or position occurs at a later time than another stance or position within a temporal sequence.
- 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_69f76e27758c81909b711cf38a130aaf |
completed | May 3, 2026, 3:47 p.m. |
| NER | Named-entity recognition | batch_6a008c77d4dc8190b342d7407eaf48fa |
completed | May 10, 2026, 1:47 p.m. |
| PD | Predicate disambiguation | batch_6a008c18531c8190bbe883b73e6d023f |
completed | May 10, 2026, 1:46 p.m. |
| PDg | Predicate description generation | batch_6a008c770df481908fe58b265fba06a3 |
completed | May 10, 2026, 1:47 p.m. |
Created at: May 3, 2026, 4:07 p.m.