Triple
T33328584
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Sherman’s Christmas gift telegram to Abraham Lincoln |
E853336
|
entity |
| Predicate | describedGift |
P190513
|
FINISHED |
| Object | the city of Savannah |
—
|
NE NERFINISHED |
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: the city of Savannah | Statement: [Sherman’s Christmas gift telegram to Abraham Lincoln, describedGift, the city of Savannah]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: describedGift Context triple: [Sherman’s Christmas gift telegram to Abraham Lincoln, describedGift, the city of Savannah]
-
A.
giftDescribedAs
Indicates that a gift is characterized or specified by a particular description or set of descriptive attributes.
-
B.
typeOfGift
Indicates the specific kind or category of gift involved in a giving or gifting relationship.
-
C.
giftItem
Indicates that one entity gives or presents an item to another entity as a gift.
-
D.
describedIn
Indicates that information about an entity is contained or documented within a specified source, such as a text, document, or media.
-
E.
giftWas
Indicates that one entity gave another entity a gift at some point in time.
- 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_69f34969614c81909cd99661b0902533 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_69fcc7779d248190afdb348a95375443 |
completed | May 7, 2026, 5:10 p.m. |
| PD | Predicate disambiguation | batch_69fcc58566a0819082d5ea36e03bf0c6 |
completed | May 7, 2026, 5:01 p.m. |
| PDg | Predicate description generation | batch_69fcc73264e08190b0b5917f32226fae |
completed | May 7, 2026, 5:09 p.m. |
Created at: May 1, 2026, 1:34 a.m.