Triple
T1526106
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Pan |
E32339
|
entity |
| Predicate | estimatedDivergenceFromHomo |
P16042
|
FINISHED |
| Object | about 5 to 8 million years ago |
—
|
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: about 5 to 8 million years ago | Statement: [Pan, estimatedDivergenceFromHomo, about 5 to 8 million years ago]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: estimatedDivergenceFromHomo Context triple: [Pan, estimatedDivergenceFromHomo, about 5 to 8 million years ago]
-
A.
earliestKnownAncestor
Indicates that one entity is the most distant (oldest) known ancestor in the lineage of another entity.
-
B.
estimatedAgeInMillionsOfYears
chosen
Indicates the approximate age of something expressed in units of millions of years.
-
C.
hasDivergence
Indicates that there is a difference, deviation, or separation between two otherwise related entities, states, or paths.
-
D.
evolvedIn
Indicates that an entity originated or developed within a specified environment, context, or location over evolutionary time.
-
E.
hasNeutralSiteHistory
Indicates that there is a recorded history of events or interactions involving the entities at a neutral (non-home) site.
- 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_69a885e9b0ac819093a9806ad0efc82c |
completed | March 4, 2026, 7:20 p.m. |
| NER | Named-entity recognition | batch_69a933ddc5a881909cdf503f2bc29bd4 |
completed | March 5, 2026, 7:42 a.m. |
| PD | Predicate disambiguation | batch_69a907ae8f688190ad9000ea1e018585 |
completed | March 5, 2026, 4:33 a.m. |
Created at: March 4, 2026, 7:26 p.m.