Triple
T3344087
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Mary Doe |
E70327
|
entity |
| Predicate | hasRightAsserted |
P21381
|
FINISHED |
| Object | right to obtain an abortion |
—
|
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: right to obtain an abortion | Statement: [Mary Doe, hasRightAsserted, right to obtain an abortion]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hasRightAsserted Context triple: [Mary Doe, hasRightAsserted, right to obtain an abortion]
-
A.
hasRightsOver
Indicates that one entity possesses legal, moral, or formal entitlements or authority over another entity.
-
B.
hasRightRecognizedIn
Indicates that an entity’s right is formally acknowledged or upheld within a specified context, system, or jurisdiction.
-
C.
hasLegalRight
chosen
Indicates that an entity possesses an officially recognized legal entitlement or permission to perform an action or hold a claim regarding another entity.
-
D.
hadRight
Indicates that an entity possessed a legal or moral entitlement to perform an action, access something, or claim something in relation to another entity or situation.
-
E.
hasAccessTo
Indicates that one entity is permitted to enter, use, or interact with another entity, resource, or location.
- 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_69ad85a405e48190b6e68de7cf9f319e |
completed | March 8, 2026, 2:20 p.m. |
| NER | Named-entity recognition | batch_69adb1f23008819084ea68b8431c50ab |
completed | March 8, 2026, 5:29 p.m. |
| PD | Predicate disambiguation | batch_69ada42df1d48190874bb05f95deefde |
completed | March 8, 2026, 4:30 p.m. |
Created at: March 8, 2026, 3:12 p.m.