Triple
T26896326
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Old Lady with the Garden |
E677906
|
entity |
| Predicate | actionOnGerda |
P9769
|
FINISHED |
| Object | combs Gerda’s hair to make her forget Kai |
—
|
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: combs Gerda’s hair to make her forget Kai | Statement: [Old Lady with the Garden, actionOnGerda, combs Gerda’s hair to make her forget Kai]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: actionOnGerda Context triple: [Old Lady with the Garden, actionOnGerda, combs Gerda’s hair to make her forget Kai]
-
A.
actionBy
Indicates that a particular action is performed or carried out by a specified agent or entity.
-
B.
actsOn
chosen
Indicates that one entity performs an action that affects, targets, or is directed toward another entity.
-
C.
commonAction
Indicates that multiple entities participate in or perform the same action or activity.
-
D.
fromAct
Indicates that an entity originates from, is produced by, or results from a specified action or event.
-
E.
causeOfAction
Indicates that one entity is the reason or basis for initiating a legal action or lawsuit against 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_69eee9befee48190a26f214faa867be7 |
completed | April 27, 2026, 4:44 a.m. |
| NER | Named-entity recognition | batch_69f61faa702c81909489a6d40e8ee023 |
completed | May 2, 2026, 4 p.m. |
| PD | Predicate disambiguation | batch_69f611af72ac819094598dd2530d7411 |
completed | May 2, 2026, 3:01 p.m. |
Created at: April 27, 2026, 5:48 a.m.