Triple
T25276203
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Southern African rail network |
E633701
|
entity |
| Predicate | hasApproximateGauge |
P160853
|
FINISHED |
| Object | 1067 mm |
—
|
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: 1067 mm | Statement: [Southern African rail network, hasApproximateGauge, 1067 mm]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasApproximateGauge Context triple: [Southern African rail network, hasApproximateGauge, 1067 mm]
-
A.
hasApproximateValue
Indicates that one entity’s value is close to, but not exactly equal to, the value of another entity within an acceptable margin of error.
-
B.
hasApproximateRate
Indicates that one entity is associated with another entity representing an estimated or non-exact rate or frequency.
-
C.
hasApproximateMemberCount
Indicates that an entity is associated with a group or collection for which only an estimated or non-exact number of members is known.
-
D.
hasApproximateUse
Indicates that one entity is used for a purpose that is similar to, but not exactly the same as, the use or function of another entity.
-
E.
hasApproximateStoreCount
Indicates that an entity is associated with an estimated or approximate number of stores, rather than an exact count.
- 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_69e75a92f48881909974ff9c11150a2e |
completed | April 21, 2026, 11:08 a.m. |
| NER | Named-entity recognition | batch_69f60ac643108190ae81561267155791 |
completed | May 2, 2026, 2:31 p.m. |
| PD | Predicate disambiguation | batch_69f602ce79ec8190b8336c2b9de18ac7 |
completed | May 2, 2026, 1:57 p.m. |
| PDg | Predicate description generation | batch_69f606c15af88190958856a9e467b826 |
completed | May 2, 2026, 2:14 p.m. |
Created at: April 21, 2026, 1:17 p.m.