Triple
T24025403
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | The Woman (Death of a Salesman) |
E594941
|
entity |
| Predicate | isUnnamedIn |
P111602
|
FINISHED |
| Object | Death of a Salesman |
—
|
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: Death of a Salesman | Statement: [The Woman (Death of a Salesman), isUnnamedIn, Death of a Salesman]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: isUnnamedIn Context triple: [The Woman (Death of a Salesman), isUnnamedIn, Death of a Salesman]
-
A.
isUnnamedBeyondDescription
Indicates that something lacks a specific name and can only be referred to or characterized in vague, indescribable, or ineffable terms.
-
B.
isNamedUnit
Indicates that an entity is a unit of measurement that has an explicit, conventional name rather than being expressed purely in derived or composite form.
-
C.
oftenUnnamedIn
chosen
Indicates that an entity frequently appears in a given context, work, or setting without being explicitly named.
-
D.
notNamedAfter
Indicates that one entity is explicitly not named in honor of, or derived from the name of, another entity.
-
E.
namedIn
Indicates that one entity is explicitly mentioned or referenced by name within another entity (such as a document, statement, or record).
- 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_69e288be2c288190a3a46006945557f7 |
completed | April 17, 2026, 7:23 p.m. |
| NER | Named-entity recognition | batch_69f1d76ada608190a9b63d07c2fa90d4 |
completed | April 29, 2026, 10:03 a.m. |
| PD | Predicate disambiguation | batch_69f17639d23c8190bed93434e2f9230a |
completed | April 29, 2026, 3:08 a.m. |
Created at: April 17, 2026, 9:53 p.m.