Triple
T23499766
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Homo erectus |
E571806
|
entity |
| Predicate | brainSizeRelativeTo |
P92568
|
FINISHED |
| Object | larger than Homo habilis |
—
|
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: larger than Homo habilis | Statement: [Homo erectus, brainSizeRelativeTo, larger than Homo habilis]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brainSizeRelativeTo Context triple: [Homo erectus, brainSizeRelativeTo, larger than Homo habilis]
-
A.
hasBrainToBodyRatio
chosen
Indicates the proportional relationship between the size or mass of an entity’s brain and the size or mass of its body.
-
B.
cranialCapacityRelativeToApes
Indicates that the cranial capacity of one entity is being compared in size or proportion to that typically found in apes.
-
C.
cranialCapacity
Indicates the volume or size of the interior space of the skull that can house the brain.
-
D.
cranialCapacityRelativeToModernHumans
Indicates how an entity’s cranial capacity compares in size to that of modern humans.
-
E.
brain
Indicates that an entity functions as the brain (central cognitive or control organ) of 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_69e245b4829881909b77a70e942bbd54 |
completed | April 17, 2026, 2:37 p.m. |
| NER | Named-entity recognition | batch_69f1a8fb71c08190a30500b3f63a9ce6 |
completed | April 29, 2026, 6:45 a.m. |
| PD | Predicate disambiguation | batch_69f0621165c08190a0b27b1319733959 |
completed | April 28, 2026, 7:30 a.m. |
Created at: April 17, 2026, 6:06 p.m.