Triple
T27353565
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Tai Tam Reservoirs |
E685623
|
entity |
| Predicate | trailNetworkLength |
P14630
|
FINISHED |
| Object | approximately 5 km (heritage trail) |
—
|
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: approximately 5 km (heritage trail) | Statement: [Tai Tam Reservoirs, trailNetworkLength, approximately 5 km (heritage trail)]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: trailNetworkLength Context triple: [Tai Tam Reservoirs, trailNetworkLength, approximately 5 km (heritage trail)]
-
A.
trailSystemLength
chosen
Indicates the total measured length of a trail system associated with an entity.
-
B.
totalRouteLength
Indicates the overall distance or length of an entire route when all its segments are combined.
-
C.
roadSystemLength
Indicates the total length or extent of a road network associated with an entity.
-
D.
networkLength
Indicates the total measured extent or distance covered by a network (e.g., of connections, links, or paths).
-
E.
roadLength
Indicates the measured distance or extent of a road, typically expressed in units of length.
- 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_69ef14887c288190931b8431fdbf53c4 |
completed | April 27, 2026, 7:47 a.m. |
| NER | Named-entity recognition | batch_69f62c1b91e881908798e4f00723efcb |
completed | May 2, 2026, 4:53 p.m. |
| PD | Predicate disambiguation | batch_69f623a91b9c8190b2e2fdbc55cb89b6 |
completed | May 2, 2026, 4:17 p.m. |
Created at: April 27, 2026, 11:50 a.m.