Triple
T3916708
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | 1986 San Salvador earthquake |
E88857
|
entity |
| Predicate | homeless |
P36920
|
FINISHED |
| Object | tens of thousands homeless |
—
|
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: tens of thousands homeless | Statement: [1986 San Salvador earthquake, homeless, tens of thousands homeless]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: homeless Context triple: [1986 San Salvador earthquake, homeless, tens of thousands homeless]
-
A.
estimatedHomeless
Indicates that a person or group is assessed or classified as likely experiencing homelessness, typically based on estimation rather than confirmed status.
-
B.
hasNumberOfHomeless
chosen
Indicates the quantified count of homeless individuals associated with a given entity or context.
-
C.
positionOnWelfare
Indicates a stance or viewpoint an entity holds regarding welfare policies or welfare-related issues.
-
D.
hasPublicHousing
Indicates that a location or jurisdiction provides or contains government-funded residential housing available to the public.
-
E.
living
Indicates that an entity is alive or currently exists in a living state.
- 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_69aed955229881909e85e73ffab1d343 |
completed | March 9, 2026, 2:29 p.m. |
| NER | Named-entity recognition | batch_69aef188b474819087680db42b04ecdd |
completed | March 9, 2026, 4:12 p.m. |
| PD | Predicate disambiguation | batch_69aee75eedcc81908088ff4dbb8be56b |
completed | March 9, 2026, 3:29 p.m. |
Created at: March 9, 2026, 3:22 p.m.