Triple
T5293
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | John Harvard |
E103
|
entity |
| Predicate | honorificAfterDeath |
P63
|
FINISHED |
| Object | college renamed Harvard College in his honor |
—
|
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: college renamed Harvard College in his honor | Statement: [John Harvard, honorificAfterDeath, college renamed Harvard College in his honor]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: honorificAfterDeath Context triple: [John Harvard, honorificAfterDeath, college renamed Harvard College in his honor]
-
A.
honorificSuffix
Indicates that one entity is a respectful or formal suffix appended to another entity’s name or title.
-
B.
honorificRank
Indicates that one entity holds a formal title or honorific status in relation to another entity.
-
C.
dateOfDeath
Indicates the specific date on which an individual or entity died.
-
D.
namedAfter
chosen
Indicates that one entity has been given its name in honor of, or derived from, another entity.
-
E.
honorLevel
Indicates the degree or status of respect, distinction, or recognition accorded to an entity relative to others.
- 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_69a238d6b47881909e68288aed2fd858 |
completed | Feb. 28, 2026, 12:37 a.m. |
| NER | Named-entity recognition | batch_69a23c24b3d08190a714126292fd5479 |
completed | Feb. 28, 2026, 12:51 a.m. |
| PD | Predicate disambiguation | batch_69a23998af288190855f0456740cbd51 |
completed | Feb. 28, 2026, 12:40 a.m. |
Created at: Feb. 28, 2026, 12:40 a.m.