Triple
T28866563
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Robert Wilson |
E729015
|
entity |
| Predicate | recentHistory |
P165680
|
FINISHED |
| Object | released from sanitarium |
—
|
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: released from sanitarium | Statement: [Robert Wilson, recentHistory, released from sanitarium]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: recentHistory Context triple: [Robert Wilson, recentHistory, released from sanitarium]
-
A.
estimatedHistory
Indicates that there is an inferred or approximated record of past states, events, or values associated with an entity or relationship.
-
B.
categoryHistory
Indicates a relationship where an entity’s past or previous category assignments are recorded or referenced over time.
-
C.
interactionHistory
Indicates that there has been one or more past interactions or exchanges between the related entities, typically capturing their sequence, timing, and possibly outcomes.
-
D.
storesHistory
Indicates that an entity retains or records past states, events, or changes over time related to another entity or process.
-
E.
primaryShowHistory
Indicates that an entity is the main or default subject whose past states, events, or changes are to be displayed in a history view.
- F. None of above. chosen
Provenance (4 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_69f031a01cbc8190ba87270bb6fe4639 |
completed | April 28, 2026, 4:03 a.m. |
| NER | Named-entity recognition | batch_69f65a1be8288190aab1e0c93472e2f0 |
completed | May 2, 2026, 8:10 p.m. |
| PD | Predicate disambiguation | batch_69f65762b5e481908a30ca963dcba4be |
completed | May 2, 2026, 7:58 p.m. |
| PDg | Predicate description generation | batch_69f658ebeca4819096beb3f98f73fe31 |
completed | May 2, 2026, 8:05 p.m. |
Created at: April 28, 2026, 6:49 a.m.