Triple
T27481045
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Nanyang Commandery |
E693602
|
entity |
| Predicate | hadHouseholds |
P162431
|
FINISHED |
| Object | over 200,000 households in Western Han |
—
|
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: over 200,000 households in Western Han | Statement: [Nanyang Commandery, hadHouseholds, over 200,000 households in Western Han]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: hadHouseholds Context triple: [Nanyang Commandery, hadHouseholds, over 200,000 households in Western Han]
-
A.
houseOrFamily
Indicates that two entities are related through a shared house, household, or family membership.
-
B.
hasHouseholdType
Indicates the type or category of household associated with an entity (e.g., family, single-person, shared, etc.).
-
C.
householdStatus
Indicates the type or condition of a person’s living arrangement within a household, such as their role, membership, or current residency status.
-
D.
householdsCensus2000
Indicates the number of households recorded in the 2000 census for a given geographic or administrative unit.
-
E.
householdsCensus2010
Indicates the number of households recorded in the 2010 census for a given geographic or administrative unit.
- F. None of above. chosen
Provenance (4 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_69ef5381f2648190a2392d0fab833095 |
completed | April 27, 2026, 12:16 p.m. |
| NER | Named-entity recognition | batch_69f62e47d5148190bff308cf49612191 |
completed | May 2, 2026, 5:03 p.m. |
| PD | Predicate disambiguation | batch_69f623aaf40081909f947431424a1d55 |
completed | May 2, 2026, 4:17 p.m. |
| PDg | Predicate description generation | batch_69f624c006788190a2f4d5015c96463f |
completed | May 2, 2026, 4:22 p.m. |
Created at: April 27, 2026, 12:59 p.m.