Triple
T9615688
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Black Maria replica |
E232212
|
entity |
| Predicate | originalLocatedIn |
P76139
|
FINISHED |
| Object | West Orange, New Jersey |
—
|
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: West Orange, New Jersey | Statement: [Black Maria replica, originalLocatedIn, West Orange, New Jersey]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: originalLocatedIn Context triple: [Black Maria replica, originalLocatedIn, West Orange, New Jersey]
-
A.
originalLocationStatus
Indicates the status or condition of an entity’s original location, such as whether it remains, has changed, or is otherwise affected.
-
B.
previouslyLocatedIn
Indicates that an entity was located in a particular place or region at some time in the past, but is not necessarily located there now.
-
C.
sourceLocatedOn
Indicates that the source entity is physically situated on the surface or area of the target entity.
-
D.
locationOfOriginals
Indicates the place where the original versions or source items of something are kept or found.
-
E.
hasOriginalLocation
chosen
Indicates that an entity was initially located or situated at a specified place or position before any change or movement occurred.
- 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_69ca84867bb88190b4b57dd5a56d5691 |
completed | March 30, 2026, 2:11 p.m. |
| NER | Named-entity recognition | batch_69cd9aabb6b88190b53547db885e0129 |
completed | April 1, 2026, 10:22 p.m. |
| PD | Predicate disambiguation | batch_69ccd5aa1d2c8190a287bf1cf4a3037e |
completed | April 1, 2026, 8:22 a.m. |
Created at: March 30, 2026, 8:09 p.m.