Triple
T28025763
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Orrorin tugenensis |
E708118
|
entity |
| Predicate | moreSpecificTime |
P97853
|
FINISHED |
| Object | Late Miocene |
—
|
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: Late Miocene | Statement: [Orrorin tugenensis, moreSpecificTime, Late Miocene]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: moreSpecificTime Context triple: [Orrorin tugenensis, moreSpecificTime, Late Miocene]
-
A.
morePreciseDate
chosen
Indicates that one date value specifies a more detailed or exact point in time than another related date value.
-
B.
timeDefinite
Indicates that the associated event or state occurs at a clearly specified, fixed point or interval in time.
-
C.
time
Indicates a temporal relationship specifying when an event occurs or how entities are ordered or related in time.
-
D.
latestTime
Indicates the most recent point in time at which the related event, state, or condition occurs or is valid among a set of possible times.
-
E.
knowledgeOfExactTime
Indicates that an entity is aware of the precise, specific time at which an event occurs or a state holds.
- 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_69ef9b6bdd9c8190bb3a574a03774ad1 |
completed | April 27, 2026, 5:22 p.m. |
| NER | Named-entity recognition | batch_69f63c6e32588190a158f8e20946b582 |
completed | May 2, 2026, 6:03 p.m. |
| PD | Predicate disambiguation | batch_69f63710d17c819084cfe96e6df334fd |
completed | May 2, 2026, 5:40 p.m. |
Created at: April 27, 2026, 8:12 p.m.