Triple
T36566057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mesohippus |
E901979
|
entity |
| Predicate | brainSizeComparedToEarlierHorses |
P185868
|
FINISHED |
| Object | larger |
—
|
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 | Statement: [Mesohippus, brainSizeComparedToEarlierHorses, larger]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: brainSizeComparedToEarlierHorses Context triple: [Mesohippus, brainSizeComparedToEarlierHorses, larger]
-
A.
cranialCapacityComparedToEarlierHominins
Indicates that the subject’s cranial capacity is being evaluated in relation to, and characterized as larger, smaller, or similar compared to, that of earlier hominin species.
-
B.
distinguishedFromHorsesBy
Indicates that one entity is characterized or identified by specific features that set it apart from horses.
-
C.
hasCranialCapacity
Indicates that one entity possesses a specific volume or size of space within the skull available for the brain.
-
D.
cranialCapacityRelativeToApes
Indicates that the cranial capacity of one entity is being compared in size or proportion to that typically found in apes.
-
E.
cranialCapacityRelativeToModernHumans
Indicates how an entity’s cranial capacity compares in size to that of modern humans.
- 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_69f76e6416708190a9754b8c52d4e453 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69f7c371931c8190afb1d4dd5157f92c |
completed | May 3, 2026, 9:51 p.m. |
| PD | Predicate disambiguation | batch_69f7c1baf25c8190a78dd54a400d2c50 |
completed | May 3, 2026, 9:44 p.m. |
| PDg | Predicate description generation | batch_69f7c3705b5c81908c84004543a71c07 |
completed | May 3, 2026, 9:51 p.m. |
Created at: May 3, 2026, 4:11 p.m.