Triple
T36196481
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Chicago criminal justice system |
E1047140
|
entity |
| Predicate | includesDefenseService |
P204781
|
FINISHED |
| Object | Cook County Public Defender’s Office |
E257079
|
NE 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: Cook County Public Defender’s Office | Statement: [Chicago criminal justice system, includesDefenseService, Cook County Public Defender’s Office]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: includesDefenseService Context triple: [Chicago criminal justice system, includesDefenseService, Cook County Public Defender’s Office]
-
A.
featuresDefenseBy
Indicates that an entity possesses or is characterized by a defense mechanism, strategy, or protective feature provided or implemented by another entity.
-
B.
recognizesDefense
Indicates that one entity acknowledges, identifies, or accepts another entity’s defensive action, strategy, or legal defense as such.
-
C.
coordinatesDefenseSupport
Indicates organizing and directing defensive assistance or protective actions among involved entities.
-
D.
providesDefence
Indicates that one entity offers protection or defensive support to another entity.
-
E.
defenseIncludes
Indicates that a defense strategy, plan, or system contains or incorporates a particular component, measure, or element as part of it.
- F. None of above. chosen
Provenance (5 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_69f76e414bdc8190996f15a544220a3d |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_6a037c92f03c8190ae2751270b195423 |
completed | May 12, 2026, 7:16 p.m. |
| NED1 | Entity disambiguation (via context triple) | batch_6a394d2c266c81908c6e721e7902fe5a |
completed | June 22, 2026, 2:56 p.m. |
| PD | Predicate disambiguation | batch_6a037a0a54cc8190868c1bfa1590d1a6 |
completed | May 12, 2026, 7:05 p.m. |
| PDg | Predicate description generation | batch_6a037c82f8c88190bd77a086023ac0e1 |
completed | May 12, 2026, 7:16 p.m. |
Created at: May 3, 2026, 4:08 p.m.