Triple
T33107914
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | theBrothers |
E847240
|
entity |
| Predicate | commendedBehavior |
P22916
|
FINISHED |
| Object | walking in the truth |
—
|
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: walking in the truth | Statement: [theBrothers, commendedBehavior, walking in the truth]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: commendedBehavior Context triple: [theBrothers, commendedBehavior, walking in the truth]
-
A.
advisedBehavior
Indicates that one entity recommends or counsels a particular behavior or course of action to another entity.
-
B.
recommendedMode
Indicates that one entity is suggested or advised as the preferred mode, method, or way of doing or experiencing something in relation to another entity.
-
C.
recommendedPolicy
Indicates that one entity suggests or endorses a particular policy for another entity or situation.
-
D.
commendedFor
chosen
Indicates that one entity has expressed praise or approval toward another entity specifically because of a particular action, quality, or achievement.
-
E.
recommendedState
Indicates that one entity is suggested or advised as the preferred state or condition for another 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_69f3495686508190b76bf20fa5e00bf7 |
completed | April 30, 2026, 12:21 p.m. |
| NER | Named-entity recognition | batch_69f7626667f48190ad90867eb67ec582 |
completed | May 3, 2026, 2:57 p.m. |
| PD | Predicate disambiguation | batch_69f76175d6608190b60b268e20f49ed9 |
completed | May 3, 2026, 2:53 p.m. |
Created at: May 1, 2026, 1:26 a.m.