Triple
T2225288
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Manzanar National Historic Site |
E48634
|
entity |
| Predicate | numberOfIncarceratedPersons |
P14018
|
FINISHED |
| Object | over 10000 |
—
|
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 10000 | Statement: [Manzanar National Historic Site, numberOfIncarceratedPersons, over 10000]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: numberOfIncarceratedPersons Context triple: [Manzanar National Historic Site, numberOfIncarceratedPersons, over 10000]
-
A.
numberOfPrisonersApproximate
Indicates an approximate count of prisoners associated with an entity or situation, rather than an exact number.
-
B.
estimatedPrisonerCount
chosen
Indicates the estimated number of prisoners associated with a particular context, such as a location, time period, or event.
-
C.
hasPrisonerPopulation
Indicates that an entity maintains or contains a population of prisoners, specifying the number or presence of incarcerated individuals associated with it.
-
D.
numberOfIndictedPersonsApproximate
Indicates an approximate count of persons who have been formally indicted in a given context or case.
-
E.
numberOfArrests
Indicates the count of times an entity has been arrested.
- 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_69a88aa51b388190949868ec9766e587 |
completed | March 4, 2026, 7:40 p.m. |
| NER | Named-entity recognition | batch_69abc03ffcbc8190a27e32af831c7be5 |
completed | March 7, 2026, 6:05 a.m. |
| PD | Predicate disambiguation | batch_69abbdac31d8819092d17815e11921e9 |
completed | March 7, 2026, 5:54 a.m. |
Created at: March 4, 2026, 7:47 p.m.