Triple
T41577
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Memorial Bridge |
E819
|
entity |
| Predicate | closedForRepairs |
P1580
|
FINISHED |
| Object | partial closures during 2015–2019 rehabilitation |
—
|
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: partial closures during 2015–2019 rehabilitation | Statement: [Memorial Bridge, closedForRepairs, partial closures during 2015–2019 rehabilitation]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: closedForRepairs Context triple: [Memorial Bridge, closedForRepairs, partial closures during 2015–2019 rehabilitation]
-
A.
maintenance
chosen
Indicates that an entity performs, requires, or is involved in upkeep, repair, or preservation activities for another entity or system.
-
B.
discontinuedIn
Indicates that an item, product, or service stopped being produced, offered, or supported starting in a specified time or place.
-
C.
openedForUse
Indicates that something has been made accessible and available for its intended operation or use.
-
D.
opened
Indicates that one entity caused another entity (such as an object, container, or passage) to change from a closed or inaccessible state to an open or accessible state.
-
E.
damagedIn
Indicates that an entity has suffered harm, impairment, or destruction as a result of a specified event, process, or condition.
- 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_69a247a8f6c08190bac804906d62ed5a |
completed | Feb. 28, 2026, 1:40 a.m. |
| NER | Named-entity recognition | batch_69a24db9527c8190816b6b25c88cb2f4 |
completed | Feb. 28, 2026, 2:06 a.m. |
| PD | Predicate disambiguation | batch_69a24ab8a8908190beec6da6694dd4c9 |
completed | Feb. 28, 2026, 1:54 a.m. |
Created at: Feb. 28, 2026, 1:46 a.m.