Triple
T1567
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | IRE Medal of Honor |
E29
|
entity |
| Predicate | associatedWithMerger |
P37
|
FINISHED |
| Object | merger of AIEE and IRE into IEEE |
—
|
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: merger of AIEE and IRE into IEEE | Statement: [IRE Medal of Honor, associatedWithMerger, merger of AIEE and IRE into IEEE]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: associatedWithMerger Context triple: [IRE Medal of Honor, associatedWithMerger, merger of AIEE and IRE into IEEE]
-
A.
mergedInto
Indicates that one entity has been combined with and absorbed into another entity, ceasing to exist as a separate unit.
-
B.
mergerYear
Indicates the year in which two or more entities formally merged into a single entity.
-
C.
relatedTo
chosen
Indicates a general, non-specific relationship or association exists between two entities.
-
D.
wasSupersededBy
Indicates that one entity has been replaced or made obsolete by another entity that takes over its role or function.
-
E.
memberOf
Indicates that an entity belongs to, is part of, or is a constituent of a larger group, organization, or collection.
- 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_69a22a285828819081a58308fb963df1 |
completed | Feb. 27, 2026, 11:35 p.m. |
| NER | Named-entity recognition | batch_69a2346846608190b6b40d31f1dbd685 |
completed | Feb. 28, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69a233c396ec8190986608d07fb251d4 |
completed | Feb. 28, 2026, 12:16 a.m. |
Created at: Feb. 27, 2026, 11:36 p.m.