Triple
T8784059
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Ai Qing |
E209000
|
entity |
| Predicate | wasRehabilitatedIn |
P29258
|
FINISHED |
| Object | late 1970s |
—
|
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: late 1970s | Statement: [Ai Qing, wasRehabilitatedIn, late 1970s]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: wasRehabilitatedIn Context triple: [Ai Qing, wasRehabilitatedIn, late 1970s]
-
A.
rehabilitatedBy
Indicates that an entity has been restored, treated, or brought back to a better or functional state through the actions or intervention of another entity.
-
B.
dateOfRehabilitation
chosen
Indicates the specific date on which a rehabilitation process, status, or measure for an entity was completed, granted, or took effect.
-
C.
wasImprisonedIn
Indicates that an entity was held in confinement or incarcerated at a particular place or facility.
-
D.
hadResidentialProgram
Indicates that an entity operated or offered a residential program in which participants lived on-site for a period of time.
-
E.
recoveredWithAidFrom
Indicates that an entity returned to a prior or improved state (such as health, function, or condition) as a result of assistance, intervention, or support from 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_69ca836168108190bb43d3dc235c1f55 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc5f7441e8819081ea0ae7bc2afde7 |
completed | March 31, 2026, 11:57 p.m. |
| PD | Predicate disambiguation | batch_69cc5c1aff3881908be6a9cbc9f50461 |
completed | March 31, 2026, 11:43 p.m. |
Created at: March 30, 2026, 6:42 p.m.