Triple
T38543890
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Vindija Cave |
E924911
|
entity |
| Predicate | providedDNAFor |
P198843
|
FINISHED |
| Object | draft Neanderthal genome |
—
|
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: draft Neanderthal genome | Statement: [Vindija Cave, providedDNAFor, draft Neanderthal genome]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: providedDNAFor Context triple: [Vindija Cave, providedDNAFor, draft Neanderthal genome]
-
A.
providedInformationTo
Indicates that one entity has supplied or communicated information to another entity.
-
B.
DNAAnalysis
Indicates that one entity performs or undergoes the examination and interpretation of DNA from another entity or source.
-
C.
geneticMaterial
Indicates that one entity serves as the hereditary or genetic substance (e.g., DNA or RNA) of another entity.
-
D.
providedFor
Indicates that one entity supplies, furnishes, or makes something available to or on behalf of another entity for its use or benefit.
-
E.
createsFromDNA
Indicates that one entity brings another entity into existence by using DNA as the source or template.
- 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_69f76eadeac081909cdfdd0474cb6765 |
completed | May 3, 2026, 3:50 p.m. |
| NER | Named-entity recognition | batch_69ff0d80c0dc81909fbd12285c7a45c0 |
completed | May 9, 2026, 10:33 a.m. |
| PD | Predicate disambiguation | batch_69ff0cd03e78819094895058f925fbfa |
completed | May 9, 2026, 10:30 a.m. |
| PDg | Predicate description generation | batch_69ff0d800ee88190835e233d9e846cdb |
completed | May 9, 2026, 10:33 a.m. |
Created at: May 3, 2026, 4:32 p.m.