Triple
T20985071
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Victoria Climbié Inquiry |
E516871
|
entity |
| Predicate | identifiedFailure |
P77548
|
FINISHED |
| Object | poor information sharing between agencies |
—
|
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: poor information sharing between agencies | Statement: [Victoria Climbié Inquiry, identifiedFailure, poor information sharing between agencies]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: identifiedFailure Context triple: [Victoria Climbié Inquiry, identifiedFailure, poor information sharing between agencies]
-
A.
failureCause
chosen
Indicates that one event, condition, or factor is the reason or source that caused a particular failure to occur.
-
B.
failureCrystallizedBy
Indicates that a failure or breakdown is concretely manifested, solidified, or made clearly observable through a particular event, condition, or outcome.
-
C.
failureModel
Indicates the type or structure of how a system, component, or process can fail or behaves when failures occur.
-
D.
typeOfFailure
Indicates the specific kind or category of failure that occurred in relation to an entity or process.
-
E.
failureEvent
Indicates that an action, process, or system has not achieved its intended outcome, resulting in a failure occurrence.
- 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.