Triple
T6268969
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | That's What Friends Are For |
E140481
|
entity |
| Predicate | associatedWithEpidemic |
P69065
|
FINISHED |
| Object | HIV/AIDS epidemic |
—
|
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: HIV/AIDS epidemic | Statement: [That's What Friends Are For, associatedWithEpidemic, HIV/AIDS epidemic]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithEpidemic Context triple: [That's What Friends Are For, associatedWithEpidemic, HIV/AIDS epidemic]
-
A.
associatedPandemic
Indicates a relationship where something (such as an event, condition, or entity) is linked or connected to a specific pandemic.
-
B.
epidemicStartAssociation
Indicates an association between an entity and the onset or initial occurrence of an epidemic event.
-
C.
associatedOutbreak
Indicates that one entity (such as a case, location, or event) is linked to or involved in a particular outbreak.
-
D.
epidemicType
Indicates the classification of an epidemic according to its nature, pattern, or mode of spread.
-
E.
experiencedEpidemic
Indicates that an entity has undergone or been affected by an epidemic event.
- 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_69c008cabc4081909723e2547c9d6cc0 |
completed | March 22, 2026, 3:20 p.m. |
| NER | Named-entity recognition | batch_69c063a28da081909f4bec8f7c1dedef |
completed | March 22, 2026, 9:48 p.m. |
| PD | Predicate disambiguation | batch_69c05606fb50819082d1a5a91e5030b6 |
completed | March 22, 2026, 8:50 p.m. |
| PDg | Predicate description generation | batch_69c056c965ac8190b938502fa8c74e1b |
completed | March 22, 2026, 8:53 p.m. |
Created at: March 22, 2026, 4:25 p.m.