Triple
T33665663
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Bradford (frequent visitor and landholder) |
E862483
|
entity |
| Predicate | hasPropertyIn |
P203643
|
FINISHED |
| Object | Marshfield |
E155749
|
NE 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: Marshfield | Statement: [William Bradford (frequent visitor and landholder), hasPropertyIn, Marshfield]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasPropertyIn Context triple: [William Bradford (frequent visitor and landholder), hasPropertyIn, Marshfield]
-
A.
haveProperty
Indicates that an entity possesses, exhibits, or is characterized by a particular property or attribute.
-
B.
hasPropertyT
Indicates that an entity possesses or is characterized by a specific property T.
-
C.
hasAncestralProperty
Indicates that an entity possesses a property, trait, or characteristic that originates from or is inherited through its ancestors.
-
D.
hasPropertyFlag
Indicates that an entity possesses a specific property denoted by a particular flag or marker.
-
E.
hasSubproperty
Indicates that one property is a more specific version of another property, inheriting its meaning and constraints.
- F. None of above. chosen
Provenance (5 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_69f34984c4008190bb82f33a7819da64 |
completed | April 30, 2026, 12:22 p.m. |
| NER | Named-entity recognition | batch_6a01bb9c33cc8190a95ba124d97edf99 |
completed | May 11, 2026, 11:21 a.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a363c8c00d88190bd9883210d1eec29 |
completed | June 20, 2026, 7:09 a.m. |
| PD | Predicate disambiguation | batch_6a01bb6772148190a243d1141ad0a237 |
completed | May 11, 2026, 11:20 a.m. |
| PDg | Predicate description generation | batch_6a01bb9b5dc481908430714ad0ab891d |
completed | May 11, 2026, 11:20 a.m. |
Created at: May 1, 2026, 1:42 a.m.