Triple
T2923790
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lugdunum |
E78794
|
entity |
| Predicate | approximatePeakPopulation |
P6809
|
FINISHED |
| Object | tens of thousands of inhabitants |
—
|
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: tens of thousands of inhabitants | Statement: [Lugdunum, approximatePeakPopulation, tens of thousands of inhabitants]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: approximatePeakPopulation Context triple: [Lugdunum, approximatePeakPopulation, tens of thousands of inhabitants]
-
A.
hasPopulationApproximate
Indicates that an entity has an estimated or approximate population size, rather than an exact count.
-
B.
populationAtPeak
chosen
Indicates that an entity’s population size is measured at its highest recorded level during a specified time or condition.
-
C.
approximatePopulationTrend
Indicates an estimated or generalized pattern of how a population changes over time (e.g., increasing, decreasing, or stable) rather than an exact count.
-
D.
metropolitanAreaPopulationApproximate
Indicates that the predicate specifies an approximate total population size for a given metropolitan area.
-
E.
hasPopulationAsOf
Indicates that a population count is associated with a specific point or date in time when that population figure was valid or recorded.
- 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_69ad8b0d40b481908bc2a5fa2e73c3fb |
completed | March 8, 2026, 2:43 p.m. |
| NER | Named-entity recognition | batch_69ad97fd89d88190bc7db4b39058ae3a |
completed | March 8, 2026, 3:38 p.m. |
| PD | Predicate disambiguation | batch_69ad9603ddd88190b8bf91bc7517cc21 |
completed | March 8, 2026, 3:30 p.m. |
Created at: March 8, 2026, 2:55 p.m.