Triple
T8683057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dmanisi |
E206084
|
entity |
| Predicate | approximateAgeInYears |
P52881
|
FINISHED |
| Object | 1.8 million years |
—
|
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: 1.8 million years | Statement: [Dmanisi, approximateAgeInYears, 1.8 million years]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximateAgeInYears Context triple: [Dmanisi, approximateAgeInYears, 1.8 million years]
-
A.
approximateAgeMa
Indicates that one entity has an estimated or approximate age value relative to another reference (such as a person or event).
-
B.
approximateAgeBeforePresent
chosen
Indicates that one entity’s age is an estimated value measured as a time interval before the present moment.
-
C.
typicalAge
Indicates the usual or characteristic age associated with an entity, event, or condition.
-
D.
containsAge
Indicates that one entity includes or specifies the age value or age-related information of another entity.
-
E.
hasAge
Indicates that an entity possesses a specific age value, typically expressed as a number of time units since its birth or creation.
- 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_69ca835379688190aa06b9d98e684d58 |
completed | March 30, 2026, 2:06 p.m. |
| NER | Named-entity recognition | batch_69cc4ae9da3c8190866e24970a7aeba3 |
completed | March 31, 2026, 10:30 p.m. |
| PD | Predicate disambiguation | batch_69cc4567b5c881908d9ec5dcfc783fac |
completed | March 31, 2026, 10:06 p.m. |
Created at: March 30, 2026, 6:32 p.m.