Triple
T20109537
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Dangling Man |
E490288
|
entity |
| Predicate | protagonistOccupationStatus |
P24370
|
FINISHED |
| Object | unemployed |
—
|
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: unemployed | Statement: [Dangling Man, protagonistOccupationStatus, unemployed]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: protagonistOccupationStatus Context triple: [Dangling Man, protagonistOccupationStatus, unemployed]
-
A.
protagonistSocialStatus
Indicates the social standing or class position held by the story’s main character in relation to others in their society.
-
B.
featuresProtagonistOccupation
Indicates that the work’s main character has a specified occupation or job role.
-
C.
protagonistStatusAtStart
Indicates the role or condition the main character is in at the beginning of the narrative or event.
-
D.
protagonistFamilyStatus
Indicates the familial role or position that a character holds in relation to the story’s protagonist.
-
E.
careerStatus
chosen
Indicates the current stage, position, or condition of an entity within its professional or occupational life.
- 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_69da62636cc08190982cc71733a17b8d |
completed | April 11, 2026, 3:01 p.m. |
| NER | Named-entity recognition | batch_69e666df1b148190a28ead2f7cce7aab |
completed | April 20, 2026, 5:48 p.m. |
| PD | Predicate disambiguation | batch_69e54cf788188190a46cc49c9ce7617f |
completed | April 19, 2026, 9:45 p.m. |
Created at: April 11, 2026, 11:28 p.m.