Triple
T20772391
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Lieutenant Theo Kojak |
E511267
|
entity |
| Predicate | previousHabit |
P121987
|
FINISHED |
| Object | cigarette smoking |
—
|
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: cigarette smoking | Statement: [Lieutenant Theo Kojak, previousHabit, cigarette smoking]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: previousHabit Context triple: [Lieutenant Theo Kojak, previousHabit, cigarette smoking]
-
A.
previousBehavior
chosen
Indicates that an entity’s past actions, conduct, or patterns of behavior are being referenced in relation to a current context or evaluation.
-
B.
hasHabit
Indicates that an entity regularly performs, practices, or exhibits a particular behavior or routine.
-
C.
previousAbility
Indicates that an entity possessed a particular ability or capability at an earlier time or in a prior state.
-
D.
previousRecord
Indicates that one record directly precedes another in an ordered sequence of records.
-
E.
previousHome
Indicates that one entity served as a former or prior residence or home of another 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_69e0b4ca01148190ac018e57e0cab46f |
completed | April 16, 2026, 10:07 a.m. |
| NER | Named-entity recognition | batch_69e6c2681ff88190bfe5938c2db6b2c4 |
completed | April 21, 2026, 12:18 a.m. |
| PD | Predicate disambiguation | batch_69e5c0550ec481908a0877fb2409d983 |
completed | April 20, 2026, 5:57 a.m. |
Created at: April 16, 2026, 12:37 p.m.