Triple
T26977067
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Kolam people |
E679485
|
entity |
| Predicate | vulnerableGroup |
P161408
|
FINISHED |
| Object | socially marginalized community |
—
|
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: socially marginalized community | Statement: [Kolam people, vulnerableGroup, socially marginalized community]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: vulnerableGroup Context triple: [Kolam people, vulnerableGroup, socially marginalized community]
-
A.
vulnerableGroup
chosen
Indicates that the referenced group is at increased risk of harm, disadvantage, or negative outcomes compared to others.
-
B.
victimGroup
Indicates that one group or entity is the target or recipient of harm, abuse, or wrongdoing caused by another.
-
C.
victimGroupContext
Indicates the contextual circumstances or setting in which a victim group is targeted, affected, or involved in an event or action.
-
D.
victimGroupHelped
Indicates that assistance, support, or aid was provided to a group identified as victims.
-
E.
ethnicGroupProtected
Indicates that an entity is legally or formally recognized as a protected ethnic group, typically afforded specific rights, safeguards, or anti-discrimination protections.
- 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_69eeeb507a7081909d516e1fa08b7d29 |
completed | April 27, 2026, 4:51 a.m. |
| NER | Named-entity recognition | batch_69f621537bfc8190b006eb8da71c2161 |
completed | May 2, 2026, 4:07 p.m. |
| PD | Predicate disambiguation | batch_69f61b3ee7b08190a0a1bc5d26b757aa |
completed | May 2, 2026, 3:41 p.m. |
Created at: April 27, 2026, 6:43 a.m.