Triple
T26775813
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Port Preference Clause |
E670116
|
entity |
| Predicate | isLocatedInTextOf |
P134241
|
FINISHED |
| Object | Article I, Section 9 of the United States Constitution |
—
|
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: Article I, Section 9 of the United States Constitution | Statement: [Port Preference Clause, isLocatedInTextOf, Article I, Section 9 of the United States Constitution]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isLocatedInTextOf Context triple: [Port Preference Clause, isLocatedInTextOf, Article I, Section 9 of the United States Constitution]
-
A.
locatedInTextualSource
chosen
Indicates that information about an entity or relation appears within, or is documented by, a specific textual source.
-
B.
positionInText
Indicates the specific location or span that something occupies within a text.
-
C.
textLocation
Indicates the spatial or positional relationship of a piece of text within a larger document, page, or layout.
-
D.
locationInDocument
Indicates that one entity specifies where another entity is situated or referenced within a document.
-
E.
locatedInArticle
Indicates that one item (such as a section, figure, or concept) appears within or is contained in a specific article.
- 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_69eeb31c925881909b597f6e40056d28 |
completed | April 27, 2026, 12:51 a.m. |
| NER | Named-entity recognition | batch_69f674e06c9481909ed0ea736408f0d7 |
completed | May 2, 2026, 10:04 p.m. |
| PD | Predicate disambiguation | batch_69f673c2f81c8190bf369226306eef09 |
completed | May 2, 2026, 9:59 p.m. |
Created at: April 27, 2026, 4:04 a.m.