Triple
T20984980
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Local Safeguarding Children Boards |
E516869
|
entity |
| Predicate | typeOfHarmAddressed |
P36524
|
FINISHED |
| Object | abuse |
—
|
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: abuse | Statement: [Local Safeguarding Children Boards, typeOfHarmAddressed, abuse]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: typeOfHarmAddressed Context triple: [Local Safeguarding Children Boards, typeOfHarmAddressed, abuse]
-
A.
threatTypeAddressed
Indicates that a given action, measure, or entity is specifically intended to counter or mitigate a particular type of threat.
-
B.
typeOfVictimization
Indicates the specific kind or category of harmful act, abuse, or exploitation experienced by a victim.
-
C.
typeOfAbuse
chosen
Indicates the specific kind or category of abusive behavior that one entity inflicts on another.
-
D.
recognizedHarm
Indicates that an entity has identified or acknowledged the existence or occurrence of harm affecting another entity or situation.
-
E.
victimCategory
Indicates the classification or type of victim associated with an event, action, or harmful outcome.
- 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_69e0b4ffac148190bbade9f0eceb660b |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6fbe218748190a987b9f922d9be1b |
completed | April 21, 2026, 4:24 a.m. |
| PD | Predicate disambiguation | batch_69e5dbec80708190a49bccab7ff97e7b |
completed | April 20, 2026, 7:55 a.m. |
Created at: April 16, 2026, 1:48 p.m.