Triple
T3632538
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Benjy Compson |
E76989
|
entity |
| Predicate | upsetBy |
P25451
|
FINISHED |
| Object | changes in routine |
—
|
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: changes in routine | Statement: [Benjy Compson, upsetBy, changes in routine]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: upsetBy Context triple: [Benjy Compson, upsetBy, changes in routine]
-
A.
upset
chosen
Indicates that one entity causes another to feel distressed, unhappy, or emotionally disturbed.
-
B.
correctsAberration
Indicates that one entity counteracts, fixes, or compensates for an error, flaw, or deviation present in another entity.
-
C.
opposedBy
Indicates that one entity actively resists, disagrees with, or works against the actions, views, or position of another entity.
-
D.
feltIn
Indicates that a sensation, emotion, or effect is experienced within a particular location, context, or entity.
-
E.
reaction
Indicates a chemical or physical process in which one set of substances or conditions transforms into another, often involving interaction, change, or response between entities.
- 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_69ad85dc03948190b35b7189e4175bcc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc30251d881908284edeb7fe69ad8 |
completed | March 8, 2026, 6:42 p.m. |
| PD | Predicate disambiguation | batch_69adb842be7c8190b7dfdb7c906f294c |
completed | March 8, 2026, 5:56 p.m. |
Created at: March 8, 2026, 3:23 p.m.