Triple
T28386833
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | HIV-1 |
E719039
|
entity |
| Predicate | firstIsolatedBy |
P39640
|
FINISHED |
| Object | Luc Montagnier’s team at the Pasteur Institute |
—
|
NE NERFINISHED |
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: Luc Montagnier’s team at the Pasteur Institute | Statement: [HIV-1, firstIsolatedBy, Luc Montagnier’s team at the Pasteur Institute]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: firstIsolatedBy Context triple: [HIV-1, firstIsolatedBy, Luc Montagnier’s team at the Pasteur Institute]
-
A.
isolatedBy
chosen
Indicates that one entity has been separated or kept apart from another entity or set of entities, preventing interaction or influence between them.
-
B.
isIsolated
Indicates that an entity exists or occurs separately from others, without direct contact, interaction, or connection.
-
C.
firstHostIsolatedFrom
Indicates that the first host is separated or kept apart from the referenced entity, with no direct interaction or connection between them.
-
D.
isolateFrom
Indicates that one entity is separated or kept apart from another entity or source.
-
E.
wasFirstIsolatedInYear
Indicates that the first successful isolation or identification of an entity occurred in the specified year.
- 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_69eff6ef211081909d31d9be5f5567e6 |
completed | April 27, 2026, 11:53 p.m. |
| NER | Named-entity recognition | batch_6a0004582bb08190b8d0b88251e8d333 |
completed | May 10, 2026, 4:06 a.m. |
| PD | Predicate disambiguation | batch_6a0003e3e5588190933beea5fb28f150 |
completed | May 10, 2026, 4:04 a.m. |
Created at: April 28, 2026, 1:10 a.m.