Triple
T48726
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | USS Arizona (BB-39) |
E957
|
entity |
| Predicate | laidDown |
P3144
|
FINISHED |
| Object | 1914-03-16 |
—
|
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: 1914-03-16 | Statement: [USS Arizona (BB-39), laidDown, 1914-03-16]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: laidDown Context triple: [USS Arizona (BB-39), laidDown, 1914-03-16]
-
A.
lays
Indicates that one entity deposits or places something, typically eggs or objects, onto a surface or in a location.
-
B.
holding
Indicates that one entity is physically grasping, carrying, or keeping another entity in its possession or control.
-
C.
backing
Indicates providing support, endorsement, or financial/resources assistance to someone or something, often enabling or strengthening their actions or position.
-
D.
settled
Indicates that an entity established residence or a stable presence in a place, typically after moving from elsewhere.
-
E.
delivered
Indicates that something has been brought or transported to a recipient or destination, typically completing a transfer or fulfillment of an order, message, or service.
- 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_69a2480baefc81909951b14058479aa2 |
completed | Feb. 28, 2026, 1:42 a.m. |
| NER | Named-entity recognition | batch_69a24c1a5c14819088748317a3f262c8 |
completed | Feb. 28, 2026, 1:59 a.m. |
| PD | Predicate disambiguation | batch_69a24abe7cb481908d969e54032f6c75 |
completed | Feb. 28, 2026, 1:54 a.m. |
| PDg | Predicate description generation | batch_69a24c198e74819088a211001d0b54d4 |
completed | Feb. 28, 2026, 1:59 a.m. |
Created at: Feb. 28, 2026, 1:47 a.m.