Triple
T2390407
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Cross Hall |
E48927
|
entity |
| Predicate | decorChanges |
P38144
|
FINISHED |
| Object | periodically updated to reflect different administrations |
—
|
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: periodically updated to reflect different administrations | Statement: [Cross Hall, decorChanges, periodically updated to reflect different administrations]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: decorChanges Context triple: [Cross Hall, decorChanges, periodically updated to reflect different administrations]
-
A.
decorChangedBy
Indicates that a change in decor or visual appearance was caused or brought about by a specific entity or action.
-
B.
notableChange
Indicates a significant alteration or shift in the state, condition, or characteristics of an entity or relationship.
-
C.
compositionChanged
Indicates that the makeup or constituent elements of something have been altered from a previous state.
-
D.
changesEvery
Indicates that one entity undergoes a change whenever or each time another specified condition, event, or entity changes.
-
E.
notableGUIChange
Indicates a significant modification or redesign in a system’s graphical user interface compared to its previous state.
- 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_69a88aa5f63081908d07fd302029fcbd |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc7de1478819082238e8b8f88ed06 |
completed | March 7, 2026, 6:38 a.m. |
| PD | Predicate disambiguation | batch_69abc5a1b5748190b4cd8989700f4dd2 |
completed | March 7, 2026, 6:28 a.m. |
| PDg | Predicate description generation | batch_69abc682d094819081a96ffb77c4c42a |
completed | March 7, 2026, 6:32 a.m. |
Created at: March 4, 2026, 7:57 p.m.