Triple
T19960719
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cosgrove Tunnel |
E479804
|
entity |
| Predicate | publicUtilityType |
P12566
|
FINISHED |
| Object | water supply infrastructure |
—
|
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: water supply infrastructure | Statement: [Cosgrove Tunnel, publicUtilityType, water supply infrastructure]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: publicUtilityType Context triple: [Cosgrove Tunnel, publicUtilityType, water supply infrastructure]
-
A.
publicUtility
Indicates that an entity provides essential services or infrastructure for the general public’s use and benefit, typically under public regulation or oversight.
-
B.
typeOfUtility
chosen
Indicates that one entity is a specific kind or category of utility associated with another entity.
-
C.
utility
Indicates that something provides usefulness, benefit, or practical value to an entity or in a given context.
-
D.
usageType
Indicates the specific manner, purpose, or context in which something is used or intended to be used.
-
E.
commonFor
Indicates that something is typical, usual, or frequently occurring for a given entity or context.
- 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_69d8e523c19881909f9197037200dde6 |
completed | April 10, 2026, 11:55 a.m. |
| NER | Named-entity recognition | batch_69e65af4520c81909986a47289ba801e |
completed | April 20, 2026, 4:57 p.m. |
| PD | Predicate disambiguation | batch_69e537f7e4848190b431a69ec3f1b609 |
completed | April 19, 2026, 8:15 p.m. |
Created at: April 10, 2026, 1:54 p.m.