Triple
T15199
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Harvard Art Museums |
E303
|
entity |
| Predicate | reopened |
P421
|
FINISHED |
| Object | 2014 |
—
|
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: 2014 | Statement: [Harvard Art Museums, reopened, 2014]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: reopened Context triple: [Harvard Art Museums, reopened, 2014]
-
A.
opened
chosen
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.
-
B.
reconstructedAfter
Indicates that one entity has been rebuilt, restored, or reassembled following the occurrence or existence of another entity or event.
-
C.
rejectedBy
Indicates that one entity has been refused, dismissed, or not accepted by another entity.
-
D.
submittedTo
Indicates that one entity has formally sent or presented something (such as a document, request, or work) to another entity for consideration, review, or processing.
-
E.
backing
Indicates providing support, endorsement, or financial/resources assistance to someone or something, often enabling or strengthening their actions or position.
- 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_69a23d7ad88c8190bffe8ab091d86642 |
completed | Feb. 28, 2026, 12:57 a.m. |
| NER | Named-entity recognition | batch_69a240b249788190af8dbf7e80e9c91b |
completed | Feb. 28, 2026, 1:11 a.m. |
| PD | Predicate disambiguation | batch_69a23feae8c481908d8c50faac01fc5c |
completed | Feb. 28, 2026, 1:07 a.m. |
Created at: Feb. 28, 2026, 1:02 a.m.