Triple
T23561122
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Will Truman |
E579237
|
entity |
| Predicate | catchallDescription |
P74595
|
FINISHED |
| Object | witty, neurotic gay lawyer and best friend of Grace Adler on Will & Grace |
—
|
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: witty, neurotic gay lawyer and best friend of Grace Adler on Will & Grace | Statement: [Will Truman, catchallDescription, witty, neurotic gay lawyer and best friend of Grace Adler on Will & Grace]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: catchallDescription Context triple: [Will Truman, catchallDescription, witty, neurotic gay lawyer and best friend of Grace Adler on Will & Grace]
-
A.
targetDescription
Indicates that an entity provides a textual explanation or characterization of a specified target entity or concept.
-
B.
alternateDescription
chosen
Indicates that an entity has an additional or substitute textual description that can be used in place of its primary description.
-
C.
backDescription
Indicates that an entity provides a description or textual information specifically about the back side or rear view of another entity.
-
D.
followUpDescription
Indicates that one entity provides additional information, clarification, or continuation related to a prior action, event, or communication involving another entity.
-
E.
catchStyle
Indicates the manner or technique with which something is caught (e.g., how an object, ball, or entity is captured or received).
- 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_69e245fe24588190888f3aec8407d8e3 |
completed | April 17, 2026, 2:38 p.m. |
| NER | Named-entity recognition | batch_69f1af680ee88190a23a6f9fed7ae757 |
completed | April 29, 2026, 7:12 a.m. |
| PD | Predicate disambiguation | batch_69f118afabd88190bd88f49597d120e8 |
completed | April 28, 2026, 8:29 p.m. |
Created at: April 17, 2026, 6:17 p.m.