Triple
T3644557
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Quentin Compson |
E77265
|
entity |
| Predicate | obsessionWith |
P49999
|
FINISHED |
| Object | his sister Caddy |
—
|
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: his sister Caddy | Statement: [Quentin Compson, obsessionWith, his sister Caddy]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: obsessionWith Context triple: [Quentin Compson, obsessionWith, his sister Caddy]
-
A.
correctsAberration
Indicates that one entity counteracts, fixes, or compensates for an error, flaw, or deviation present in another entity.
-
B.
oftenDedicatedTo
Indicates that something is frequently or habitually devoted, assigned, or committed to a particular purpose, activity, or recipient.
-
C.
obligation
Indicates that one entity is bound or required to perform a duty, action, or fulfill a condition toward another entity or according to a rule or agreement.
-
D.
behaviorObserved
Indicates that a particular behavior or action has been witnessed, recorded, or detected in relation to an entity or context.
-
E.
associatedCurse
Indicates that one entity is linked to, affected by, or bears responsibility for a particular curse related to another entity.
- F. None of above. chosen
Provenance (4 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_69ad85de1b988190a45f8dbfebc806fc |
completed | March 8, 2026, 2:21 p.m. |
| NER | Named-entity recognition | batch_69adc35c28908190b253f4835918a2b4 |
completed | March 8, 2026, 6:43 p.m. |
| PD | Predicate disambiguation | batch_69adb8445b2c8190ab07f6ad4e010d0e |
completed | March 8, 2026, 5:56 p.m. |
| PDg | Predicate description generation | batch_69adb8e4ba948190a9b777cf7f788b96 |
completed | March 8, 2026, 5:59 p.m. |
Created at: March 8, 2026, 3:24 p.m.