Triple
T28212902
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Anu Singh |
E711222
|
entity |
| Predicate | defenceArgument |
P36520
|
FINISHED |
| Object | mental illness |
—
|
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: mental illness | Statement: [Anu Singh, defenceArgument, mental illness]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: defenceArgument Context triple: [Anu Singh, defenceArgument, mental illness]
-
A.
defenseArgument
chosen
Indicates that an entity presents or supports a line of reasoning intended to defend or justify another entity, often in a legal or argumentative context.
-
B.
defendedAs
Indicates that one entity is presented, argued, or justified as being equivalent to or serving the role of another entity in a defensive or protective context.
-
C.
defends
Indicates that one entity protects or supports another entity against attack, criticism, or harm.
-
D.
defendedOn
Indicates that one entity protected, supported, or argued in favor of another entity during a specific time or event.
-
E.
providesDefence
Indicates that one entity offers protection or defensive support to 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_69efb51cb5288190818c1f63a266af11 |
completed | April 27, 2026, 7:12 p.m. |
| NER | Named-entity recognition | batch_69f6aaf50be08190a2b62a6d881f8aee |
completed | May 3, 2026, 1:55 a.m. |
| PD | Predicate disambiguation | batch_69f6aa1c555081908787dbf76147f180 |
completed | May 3, 2026, 1:51 a.m. |
Created at: April 27, 2026, 10:40 p.m.