Triple
T15950024
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Druitt (Sanctuary) |
E386789
|
entity |
| Predicate | isAbnormal |
P56306
|
FINISHED |
| Object | true |
—
|
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: true | Statement: [John Druitt (Sanctuary), isAbnormal, true]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isAbnormal Context triple: [John Druitt (Sanctuary), isAbnormal, true]
-
A.
hasAnomaly
Indicates that an entity exhibits, contains, or is associated with an irregular, abnormal, or unexpected condition or feature.
-
B.
isNormalIn
Indicates that one group is a normal subgroup of another group, meaning it is invariant under conjugation by elements of the larger group.
-
C.
hasAberrationCharacteristics
chosen
Indicates that an entity exhibits traits or properties that deviate from what is considered normal, standard, or expected.
-
D.
isSuspiciousOf
Indicates that one entity believes another entity or situation may be untrustworthy, harmful, or involved in wrongdoing.
-
E.
isUnstable
Indicates that the subject lacks stability or consistency, often changing, fluctuating, or failing to remain in a steady state.
- 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_69d86da882448190a82ea962fe343b79 |
completed | April 10, 2026, 3:25 a.m. |
| NER | Named-entity recognition | batch_69e17d4d08f481909f38b75e3f42d9ab |
completed | April 17, 2026, 12:22 a.m. |
| PD | Predicate disambiguation | batch_69e142d37cd88190ab50760f1783e20c |
completed | April 16, 2026, 8:13 p.m. |
Created at: April 10, 2026, 4:53 a.m.