Triple
T36219651
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | William Brazel |
E1047809
|
entity |
| Predicate | foundObjectDescribedAs |
P115430
|
FINISHED |
| Object | metallic debris field |
—
|
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: metallic debris field | Statement: [William Brazel, foundObjectDescribedAs, metallic debris field]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: foundObjectDescribedAs Context triple: [William Brazel, foundObjectDescribedAs, metallic debris field]
-
A.
foundAs
chosen
Indicates that one entity is discovered, identified, or observed in the role, form, or state represented by another entity.
-
B.
foundWith
Indicates that one entity is discovered, observed, or obtained in the presence or company of another entity.
-
C.
foundOver
Indicates that one entity has discovered or identified another entity located above or higher than a reference point or surface.
-
D.
foundUnder
Indicates that one entity is located beneath or below another entity in a way that it can be discovered or retrieved from that position.
-
E.
foundAfter
Indicates that one entity is discovered or located at a point in time later than another specified entity.
- 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_69f76e42c878819095c8d19c0267fb87 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69ff1e3e13c08190bb8990c44716b746 |
completed | May 9, 2026, 11:45 a.m. |
| PD | Predicate disambiguation | batch_69ff1dfcaf2c8190aaf2b428d57b7782 |
completed | May 9, 2026, 11:43 a.m. |
Created at: May 3, 2026, 4:09 p.m.