Triple
T4155057
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Madrid Agreement |
E91395
|
entity |
| Predicate | revisionHistory |
P21515
|
FINISHED |
| Object | revised at Brussels in 1900 |
—
|
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: revised at Brussels in 1900 | Statement: [Madrid Agreement, revisionHistory, revised at Brussels in 1900]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: revisionHistory Context triple: [Madrid Agreement, revisionHistory, revised at Brussels in 1900]
-
A.
revisionKnownAs
Indicates that a particular revision of an entity is referred to or identified by a specific alternative name or label.
-
B.
upgradeHistory
Indicates the record of changes where one version, state, or configuration has been replaced or improved by another over time.
-
C.
revisionOf
Indicates that one entity is a modified or updated version of another earlier entity.
-
D.
includesChangeHistory
chosen
Indicates that the subject maintains or contains a record of past modifications or changes made to it.
-
E.
ownershipHistory
Indicates the sequence of past and present owners associated with an entity over time.
- 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_69aed9626ebc8190a39de631788bea3e |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69af0321eee88190871c1d4bf44a5007 |
completed | March 9, 2026, 5:28 p.m. |
| PD | Predicate disambiguation | batch_69af018dc90c8190a754b1bfbc802e80 |
completed | March 9, 2026, 5:21 p.m. |
Created at: March 9, 2026, 3:44 p.m.